Instructions to use systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16")
model = AutoModelForCausalLM.from_pretrained("systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16", device_map="auto")
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 Settings

vLLM

How to use systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16

SGLang

How to use systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 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 "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16" \
    --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": "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16",
		"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 "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16" \
        --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": "systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 with Docker Model Runner:
```
docker model run hf.co/systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16
```

Qwen3-Coder-30B-A3B-Instruct-W4A16 / README.md

tjwebb

Model card: quantized with llm-compressor on H200; for 2x A2 via vLLM

5860164 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

3.13 kB

	---
	license: apache-2.0
	license_link: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE
	base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
	base_model_relation: quantized
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- qwen3_moe
	- moe
	- code
	- quantized
	- int4
	- w4a16
	- compressed-tensors
	- llm-compressor
	- vllm
	---

	# Qwen3-Coder-30B-A3B-Instruct-W4A16

	W4A16 (INT4 group-128 weights + FP16 activations) quantization of
	[Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct).

	- Quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) on an
	NVIDIA H200, in the
	[compressed-tensors](https://github.com/neuralmagic/compressed-tensors) `pack-quantized`
	format.
	- **Designed for inference on 2× NVIDIA A2 (16 GB, Ampere SM 8.6) with
	[vLLM](https://github.com/vllm-project/vllm)** (tensor-parallel across the two cards).

	The point of this build is to fit this 30B-A3B MoE onto small, FP8-less GPUs like the
	A2, where BF16 (~57 GB) and INT8 (~30 GB) don't fit. At 4-bit the checkpoint is ~16 GB
	(~8 GB/GPU at TP=2), running via the Marlin INT4 kernel — which, unlike FP8 / W4AFP8, works
	on Ampere.

	## What's quantized

	\| Quantized → INT4 (g128, symmetric) \| Kept in BF16 \|
	\|---\|---\|
	\| all 128 routed experts × 48 layers \| token embeddings, `lm_head` \|
	\| attention `q/k/v/o` projections \| MoE router gates, all norms \|

	Only transformer `Linear` weights are quantized; the embedding, output head, router gates,
	and norms stay BF16 for quality. It remains a standard `Qwen3MoeForCausalLM` — full GQA
	attention, SwiGLU, 128 experts / 8 active — so it uses vLLM's mainstream MoE path.

	## Serving with vLLM

	```bash
	vllm serve systemsofrecord/Qwen3-Coder-30B-A3B-Instruct-W4A16 \
	--tensor-parallel-size 2 \
	--dtype float16 \
	--max-model-len 32768 \
	--gpu-memory-utilization 0.90 \
	--enable-auto-tool-choice \
	--tool-call-parser qwen3_coder
	```

	- No FP8 required — runs on Ampere (A2 / A10 / A30 / …) and newer.
	- KV cache is FP16 (Ampere has no FP8 KV); GQA (4 KV heads) keeps it small.
	- Needs a vLLM build with `Qwen3MoeForCausalLM` support (≥ 0.25).

	Verified: loaded and generated correct code on 2× NVIDIA A2 under vLLM 0.25.1 —
	~7.9 GB weights/GPU at TP=2, Marlin wNa16 MoE kernel, CUDA graphs captured cleanly.

	## Quantization recipe

	- Tool: llm-compressor (run on an NVIDIA H200).
	- Scheme: `W4A16` — weights 4-bit int, `group_size=128`, symmetric; activations unquantized.
	- Method: model-free RTN (round-to-nearest) weight quantization.
	- Format: `pack-quantized` (INT4 packed into INT32 + group scales).
	- Ignore (BF16): `lm_head`, `embed_tokens`, MoE router gates, norms.
	- Target: 2× NVIDIA A2 served with vLLM (TP=2).

	## License & attribution

	Apache-2.0, inherited from the base model
	[Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct).
	This repository only redistributes a quantized copy of those weights; all model
	capabilities and credit belong to the Qwen team.