Inference-supported production models - a yjernite Collection

yjernite 's Collections

Text embedding models I use

super-smol to fine-tune

Models for local deployment

Inference-supported production models

Document processing

Inference-supported production models

updated 6 days ago

List of recent models to use through HF inference providers

CohereLabs/command-a-vision-07-2025

Image-Text-to-Text • 112B • Updated Oct 30, 2025 • 44.6k • • 88
Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • Updated Sep 17, 2025 • 160k • • 773
Qwen/Qwen3-32B

Text Generation • Updated Jul 26, 2025 • 2.36M • • 683

Note This is hybrid mode, so requires /no_think to skip reasoning and extracting the final result
openai/gpt-oss-120b

Text Generation • 120B • Updated Aug 26, 2025 • 3.49M • • 4.71k

Note Still misrepresents social issues as per model spec :|
moonshotai/Kimi-K2-Instruct

Text Generation • 1T • Updated Jan 30 • 257k • • 2.34k
zai-org/GLM-4.5-Air

Text Generation • 110B • Updated Aug 11, 2025 • 387k • • 598
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • Updated Aug 17, 2025 • 67.6k • • 404
zai-org/GLM-4.5

Text Generation • 358B • Updated Aug 11, 2025 • 70.2k • • 1.4k
Qwen/Qwen3-Next-80B-A3B-Instruct

Text Generation • 81B • Updated Sep 17, 2025 • 304k • • 1.01k
zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 36.2k • • 1.21k
Qwen/Qwen3-4B-Instruct-2507

Text Generation • 4B • Updated Sep 17, 2025 • 9.69M • • 813
HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated Sep 10, 2025 • 445k • 936
MiniMaxAI/MiniMax-M2

Text Generation • 229B • Updated Dec 23, 2025 • 64.1k • • 1.49k
allenai/Olmo-3-7B-Instruct

Text Generation • 528k • Updated Jan 5 • 606k • • 127
moonshotai/Kimi-K2.5

Image-Text-to-Text • 1.1T • Updated Feb 27 • 5.22M • • 2.75k
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Text Generation • 32B • Updated Mar 15 • 715k • • 336
MiniMaxAI/MiniMax-M2.7

Text Generation • 229B • Updated 2 days ago • 289k • • 977