Instructions to use mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ")
model = AutoModelForCausalLM.from_pretrained("mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ

SGLang

How to use mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ with Docker Model Runner:
```
docker model run hf.co/mattbucci/Qwen3-Coder-30B-A3B-REAP-AWQ
```

mattbucci commited on 25 days ago

Commit

8166241

verified ·

1 Parent(s): e363ec5

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -18,6 +18,8 @@ license: apache-2.0
 # Qwen3-Coder-30B-A3B-REAP AWQ 4-bit
 AWQ 4-bit quantization of a self-built REAP-pruned variant of [Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), calibrated with thinking + code data, optimized for AMD RDNA4 (gfx1201) inference with [SGLang](https://github.com/sgl-project/sglang).
 ## Model Details

 # Qwen3-Coder-30B-A3B-REAP AWQ 4-bit
+> ⚠️ **VALIDATION FAILED 2026-04-29 — DO NOT USE.** Initial smoke test on the AWQ output produces gibberish (`def count_vowels(s):` → `sweat sweat aster aster…`, both `/v1/chat/completions` and `/v1/completions`). The end-to-end pipeline (REAP+REAM merge → AWQ calib → CT→native conversion → audit) all reported success at the file-format level, but the resulting weights are unusable for inference. Likely root cause: insufficient AWQ calibration coverage (256 samples × 1024 tokens) for a 96-expert MoE post-merge, or weight corruption introduced by the REAP+REAM merge step. **For a working REAP variant of this base, use [`mattbucci/Qwen3-Coder-REAP-25B-A3B-AWQ`](https://huggingface.co/mattbucci/Qwen3-Coder-REAP-25B-A3B-AWQ)** (Cerebras prune, validated, 88/300 on SWE-bench Lite). This repo will be either fixed or removed; tracking under task #52 in the [RDNA4 inference repo](https://github.com/mattbucci/2x-R9700-RDNA4-GFX1201-sglang-inference).
 AWQ 4-bit quantization of a self-built REAP-pruned variant of [Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), calibrated with thinking + code data, optimized for AMD RDNA4 (gfx1201) inference with [SGLang](https://github.com/sgl-project/sglang).
 ## Model Details