ErazerControl commited on
Commit
e0b4570
·
verified ·
1 Parent(s): 84a8fe7

update phi-4-multimodal and whisper

Browse files
Files changed (1) hide show
  1. README.md +76 -74
README.md CHANGED
@@ -1,75 +1,77 @@
1
-
2
- # Download
3
-
4
- Download a specific WebGPU model:
5
-
6
- ```bash
7
- huggingface-cli download webai-community/ai-models --include "ai-models/<MODEL_NAME>/onnx-webgpu/*" --local-dir .
8
- ```
9
-
10
- Download all WebGPU models:
11
-
12
- ```bash
13
- huggingface-cli download webai-community/ai-models --include "*/onnx-webgpu/*" --local-dir .
14
- ```
15
-
16
- # Model List
17
-
18
- | model name | params size | gguf model | ort webgpu model | model info |
19
- | --- | --- | --- | --- | --- |
20
- | Phi-4-mini-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-4-mini-instruct/README.md) |
21
- | Phi-4-mini-reasoning | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-reasoning/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-reasoning/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-4-mini-reasoning/README.md) |
22
- | Phi-3.5-mini-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3.5-mini-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3.5-mini-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3.5-mini-instruct/README.md) |
23
- | Phi-3-mini-4k-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-4k-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-4k-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3-mini-4k-instruct/README.md) |
24
- | Phi-3-mini-128k-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-128k-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-128k-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3-mini-128k-instruct/README.md) |
25
- | Qwen3-0.6B | 0.6B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-0.6B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-0.6B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-0.6B/README.md) |
26
- | Qwen3-1.7B | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-1.7B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-1.7B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-1.7B/README.md) |
27
- | Qwen3-4B | 4B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-4B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-4B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-4B/README.md) |
28
- | Qwen3-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-8B/README.md) |
29
- | Qwen2.5-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-0.5B-Instruct/README.md) |
30
- | Qwen2.5-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-1.5B-Instruct/README.md) |
31
- | Qwen2.5-3B-Instruct | 3B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-3B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-3B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-3B-Instruct/README.md) |
32
- | Qwen2.5-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-7B-Instruct/README.md) |
33
- | Qwen2-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-0.5B-Instruct/README.md) |
34
- | Qwen2-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-1.5B-Instruct/README.md) |
35
- | Qwen2-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-7B-Instruct/README.md) |
36
- | DeepSeek-R1-Distill-Qwen-1.5B | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-1.5B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-1.5B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Qwen-1.5B/README.md) |
37
- | DeepSeek-R1-Distill-Qwen-7B | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-7B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-7B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Qwen-7B/README.md) |
38
- | DeepSeek-R1-Distill-Llama-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Llama-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Llama-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Llama-8B/README.md) |
39
- | DeepSeek-R1-0528-Qwen3-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-0528-Qwen3-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-0528-Qwen3-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-0528-Qwen3-8B/README.md) |
40
- | gemma-3-1b-it | 1B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-3-1b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-3-1b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-3-1b-it/README.md) |
41
- | gemma-2-2b-it | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-2b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-2b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2-2b-it/README.md) |
42
- | gemma-2-9b-it | 9B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-9b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-9b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2-9b-it/README.md) |
43
- | gemma-2b-it | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2b-it/README.md) |
44
- | gemma-7b-it | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-7b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-7b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-7b-it/README.md) |
45
- | internlm2_5-7b-chat | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2_5-7b-chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2_5-7b-chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2_5-7b-chat/README.md) |
46
- | internlm2-chat-1_8b | 1.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-1_8b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-1_8b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2-chat-1_8b/README.md) |
47
- | internlm2-chat-7b | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-7b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-7b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2-chat-7b/README.md) |
48
- | Nemotron-Mini-4B-Instruct | 4B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Mini-4B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Mini-4B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Nemotron-Mini-4B-Instruct/README.md) |
49
- | Nemotron-Cascade-8B-Thinking | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Cascade-8B-Thinking/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Cascade-8B-Thinking/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Nemotron-Cascade-8B-Thinking/README.md) |
50
- | SmolLM2-1.7B-Instruct | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-1.7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-1.7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-1.7B-Instruct/README.md) |
51
- | SmolLM2-360M-Instruct | 360M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-360M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-360M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-360M-Instruct/README.md) |
52
- | SmolLM2-135M-Instruct | 135M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-135M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-135M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-135M-Instruct/README.md) |
53
- | SmolLM-1.7B-Instruct | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-1.7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-1.7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-1.7B-Instruct/README.md) |
54
- | SmolLM-360M-Instruct | 360M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-360M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-360M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-360M-Instruct/README.md) |
55
- | SmolLM-135M-Instruct | 135M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-135M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-135M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-135M-Instruct/README.md) |
56
- | Yi-Coder-1.5B-Chat | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-Coder-1.5B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-Coder-1.5B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-Coder-1.5B-Chat/README.md) |
57
- | Qwen2.5-Coder-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-0.5B-Instruct/README.md) |
58
- | Qwen2.5-Coder-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-1.5B-Instruct/README.md) |
59
- | Qwen2.5-Coder-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-7B-Instruct/README.md) |
60
- | TinyLlama-1.1B-Chat-v1.0 | 1.1B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/TinyLlama-1.1B-Chat-v1.0/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/TinyLlama-1.1B-Chat-v1.0/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/TinyLlama-1.1B-Chat-v1.0/README.md) |
61
- | CodeLlama-7b-Instruct-hf | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/CodeLlama-7b-Instruct-hf/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/CodeLlama-7b-Instruct-hf/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/CodeLlama-7b-Instruct-hf/README.md) |
62
- | SOLAR-10.7B-Instruct-v1.0 | 10.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SOLAR-10.7B-Instruct-v1.0/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SOLAR-10.7B-Instruct-v1.0/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SOLAR-10.7B-Instruct-v1.0/README.md) |
63
- | gpt-oss-20b | 20B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gpt-oss-20b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gpt-oss-20b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gpt-oss-20b/README.md) |
64
- | granite-3.1-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.1-2b-instruct/README.md) |
65
- | granite-3.1-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.1-8b-instruct/README.md) |
66
- | granite-3.2-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.2-2b-instruct/README.md) |
67
- | granite-3.2-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.2-8b-instruct/README.md) |
68
- | granite-3.3-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.3-2b-instruct/README.md) |
69
- | granite-3.3-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.3-8b-instruct/README.md) |
70
- | Ministral-8B-Instruct-2410 | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Ministral-8B-Instruct-2410/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Ministral-8B-Instruct-2410/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Ministral-8B-Instruct-2410/README.md) |
71
- | Mistral-7B-Instruct-v0.2 | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.2/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.2/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-7B-Instruct-v0.2/README.md) |
72
- | Mistral-7B-Instruct-v0.3 | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.3/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.3/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-7B-Instruct-v0.3/README.md) |
73
- | Mistral-Nemo-Instruct-2407 | 12B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-Nemo-Instruct-2407/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-Nemo-Instruct-2407/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-Nemo-Instruct-2407/README.md) |
74
- | Yi-1.5-6B-Chat | 6B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-6B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-6B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-1.5-6B-Chat/README.md) |
 
 
75
  | Yi-1.5-9B-Chat | 9B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-9B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-9B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-1.5-9B-Chat/README.md) |
 
1
+
2
+ # Download
3
+
4
+ Download a specific WebGPU model:
5
+
6
+ ```bash
7
+ huggingface-cli download webai-community/ai-models --include "ai-models/<MODEL_NAME>/onnx-webgpu/*" --local-dir .
8
+ ```
9
+
10
+ Download all WebGPU models:
11
+
12
+ ```bash
13
+ huggingface-cli download webai-community/ai-models --include "*/onnx-webgpu/*" --local-dir .
14
+ ```
15
+
16
+ # Model List
17
+
18
+ | model name | params size | gguf model | ort webgpu model | model info |
19
+ | --- | --- | --- | --- | --- |
20
+ | Phi-4-mini-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-4-mini-instruct/README.md) |
21
+ | Phi-4-mini-reasoning | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-reasoning/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-mini-reasoning/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-4-mini-reasoning/README.md) |
22
+ | Phi-4-multimodal-instruct| 6B | | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-4-multimodal-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-4-multimodal-instruct/README.md) |
23
+ | Phi-3.5-mini-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3.5-mini-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3.5-mini-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3.5-mini-instruct/README.md) |
24
+ | Phi-3-mini-4k-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-4k-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-4k-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3-mini-4k-instruct/README.md) |
25
+ | Phi-3-mini-128k-instruct | 3.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-128k-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Phi-3-mini-128k-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Phi-3-mini-128k-instruct/README.md) |
26
+ | Qwen3-0.6B | 0.6B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-0.6B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-0.6B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-0.6B/README.md) |
27
+ | Qwen3-1.7B | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-1.7B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-1.7B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-1.7B/README.md) |
28
+ | Qwen3-4B | 4B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-4B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-4B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-4B/README.md) |
29
+ | Qwen3-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen3-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen3-8B/README.md) |
30
+ | Qwen2.5-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-0.5B-Instruct/README.md) |
31
+ | Qwen2.5-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-1.5B-Instruct/README.md) |
32
+ | Qwen2.5-3B-Instruct | 3B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-3B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-3B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-3B-Instruct/README.md) |
33
+ | Qwen2.5-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-7B-Instruct/README.md) |
34
+ | Qwen2-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-0.5B-Instruct/README.md) |
35
+ | Qwen2-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-1.5B-Instruct/README.md) |
36
+ | Qwen2-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2-7B-Instruct/README.md) |
37
+ | DeepSeek-R1-Distill-Qwen-1.5B | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-1.5B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-1.5B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Qwen-1.5B/README.md) |
38
+ | DeepSeek-R1-Distill-Qwen-7B | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-7B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Qwen-7B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Qwen-7B/README.md) |
39
+ | DeepSeek-R1-Distill-Llama-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Llama-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-Distill-Llama-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-Distill-Llama-8B/README.md) |
40
+ | DeepSeek-R1-0528-Qwen3-8B | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-0528-Qwen3-8B/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/DeepSeek-R1-0528-Qwen3-8B/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/DeepSeek-R1-0528-Qwen3-8B/README.md) |
41
+ | gemma-3-1b-it | 1B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-3-1b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-3-1b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-3-1b-it/README.md) |
42
+ | gemma-2-2b-it | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-2b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-2b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2-2b-it/README.md) |
43
+ | gemma-2-9b-it | 9B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-9b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2-9b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2-9b-it/README.md) |
44
+ | gemma-2b-it | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-2b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-2b-it/README.md) |
45
+ | gemma-7b-it | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gemma-7b-it/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gemma-7b-it/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gemma-7b-it/README.md) |
46
+ | internlm2_5-7b-chat | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2_5-7b-chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2_5-7b-chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2_5-7b-chat/README.md) |
47
+ | internlm2-chat-1_8b | 1.8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-1_8b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-1_8b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2-chat-1_8b/README.md) |
48
+ | internlm2-chat-7b | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-7b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/internlm2-chat-7b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/internlm2-chat-7b/README.md) |
49
+ | Nemotron-Mini-4B-Instruct | 4B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Mini-4B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Mini-4B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Nemotron-Mini-4B-Instruct/README.md) |
50
+ | Nemotron-Cascade-8B-Thinking | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Cascade-8B-Thinking/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Nemotron-Cascade-8B-Thinking/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Nemotron-Cascade-8B-Thinking/README.md) |
51
+ | SmolLM2-1.7B-Instruct | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-1.7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-1.7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-1.7B-Instruct/README.md) |
52
+ | SmolLM2-360M-Instruct | 360M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-360M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-360M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-360M-Instruct/README.md) |
53
+ | SmolLM2-135M-Instruct | 135M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-135M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM2-135M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM2-135M-Instruct/README.md) |
54
+ | SmolLM-1.7B-Instruct | 1.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-1.7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-1.7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-1.7B-Instruct/README.md) |
55
+ | SmolLM-360M-Instruct | 360M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-360M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-360M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-360M-Instruct/README.md) |
56
+ | SmolLM-135M-Instruct | 135M | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-135M-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SmolLM-135M-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SmolLM-135M-Instruct/README.md) |
57
+ | Yi-Coder-1.5B-Chat | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-Coder-1.5B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-Coder-1.5B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-Coder-1.5B-Chat/README.md) |
58
+ | Qwen2.5-Coder-0.5B-Instruct | 0.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-0.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-0.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-0.5B-Instruct/README.md) |
59
+ | Qwen2.5-Coder-1.5B-Instruct | 1.5B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-1.5B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-1.5B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-1.5B-Instruct/README.md) |
60
+ | Qwen2.5-Coder-7B-Instruct | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-7B-Instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Qwen2.5-Coder-7B-Instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Qwen2.5-Coder-7B-Instruct/README.md) |
61
+ | TinyLlama-1.1B-Chat-v1.0 | 1.1B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/TinyLlama-1.1B-Chat-v1.0/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/TinyLlama-1.1B-Chat-v1.0/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/TinyLlama-1.1B-Chat-v1.0/README.md) |
62
+ | CodeLlama-7b-Instruct-hf | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/CodeLlama-7b-Instruct-hf/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/CodeLlama-7b-Instruct-hf/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/CodeLlama-7b-Instruct-hf/README.md) |
63
+ | SOLAR-10.7B-Instruct-v1.0 | 10.7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/SOLAR-10.7B-Instruct-v1.0/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/SOLAR-10.7B-Instruct-v1.0/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/SOLAR-10.7B-Instruct-v1.0/README.md) |
64
+ | whisper-tiny | 0.39B | | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/whisper-tiny/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/whisper-tiny/README.md) |
65
+ | gpt-oss-20b | 20B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/gpt-oss-20b/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/gpt-oss-20b/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/gpt-oss-20b/README.md) |
66
+ | granite-3.1-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.1-2b-instruct/README.md) |
67
+ | granite-3.1-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.1-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.1-8b-instruct/README.md) |
68
+ | granite-3.2-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.2-2b-instruct/README.md) |
69
+ | granite-3.2-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.2-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.2-8b-instruct/README.md) |
70
+ | granite-3.3-2b-instruct | 2B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-2b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-2b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.3-2b-instruct/README.md) |
71
+ | granite-3.3-8b-instruct | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-8b-instruct/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/granite-3.3-8b-instruct/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/granite-3.3-8b-instruct/README.md) |
72
+ | Ministral-8B-Instruct-2410 | 8B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Ministral-8B-Instruct-2410/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Ministral-8B-Instruct-2410/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Ministral-8B-Instruct-2410/README.md) |
73
+ | Mistral-7B-Instruct-v0.2 | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.2/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.2/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-7B-Instruct-v0.2/README.md) |
74
+ | Mistral-7B-Instruct-v0.3 | 7B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.3/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-7B-Instruct-v0.3/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-7B-Instruct-v0.3/README.md) |
75
+ | Mistral-Nemo-Instruct-2407 | 12B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-Nemo-Instruct-2407/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Mistral-Nemo-Instruct-2407/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Mistral-Nemo-Instruct-2407/README.md) |
76
+ | Yi-1.5-6B-Chat | 6B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-6B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-6B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-1.5-6B-Chat/README.md) |
77
  | Yi-1.5-9B-Chat | 9B | [gguf](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-9B-Chat/gguf) | [onnx-webgpu](https://huggingface.co/webai-community/ai-models/tree/main/Yi-1.5-9B-Chat/onnx-webgpu) | [README](https://huggingface.co/webai-community/ai-models/blob/main/Yi-1.5-9B-Chat/README.md) |