Instructions to use tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16")
model = AutoModelForCausalLM.from_pretrained("tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16", 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 tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16

SGLang

How to use tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16 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 "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16" \
    --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": "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16",
		"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 "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16" \
        --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": "tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16 with Docker Model Runner:
```
docker model run hf.co/tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16
```

Qwen3-Coder-Next Mixed-Code Prune-70 (BF16)

Experimental expert-pruned checkpoint derived from Qwen/Qwen3-Coder-Next.

Model details

Calibration source: full HumanEval, MBPP, and BigCodeBench code datasets
Pruning method: calibration-score-based expert pruning
Experts per MoE layer: 512 -> 154 (69.92% removed)
Active experts per token: 10 (unchanged)
Layers: 48
Weight dtype: BF16
Weight payload: 51,166,017,024 bytes (~25.6B BF16 parameters)
Context configuration: inherited from the base model

Experts are renumbered after pruning. expert_mapping.csv records the retained source expert for every layer and new expert ID.

Evaluation

On the associated SWE-bench Verified evaluation, this checkpoint resolved 296/500 instances (59.2%).

Usage

Use a recent Transformers, vLLM, or SGLang release with Qwen3-Next support. This is an experimental research checkpoint; validate it for your workload before deployment.

License and attribution

This derivative checkpoint follows the Apache-2.0 license of Qwen/Qwen3-Coder-Next.

Downloads last month: 216

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for tomhu/Qwen3-Coder-Next-MixedCode-Prune70-BF16

Base model

Qwen/Qwen3-Coder-Next

Finetuned

(39)

this model