Instructions to use btbtyler09/Qwen3-Coder-Next-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use btbtyler09/Qwen3-Coder-Next-GPTQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="btbtyler09/Qwen3-Coder-Next-GPTQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("btbtyler09/Qwen3-Coder-Next-GPTQ-4bit")
model = AutoModelForCausalLM.from_pretrained("btbtyler09/Qwen3-Coder-Next-GPTQ-4bit")
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 btbtyler09/Qwen3-Coder-Next-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/btbtyler09/Qwen3-Coder-Next-GPTQ-4bit

SGLang

How to use btbtyler09/Qwen3-Coder-Next-GPTQ-4bit 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 "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit" \
    --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": "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit",
		"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 "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit" \
        --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": "btbtyler09/Qwen3-Coder-Next-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use btbtyler09/Qwen3-Coder-Next-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/btbtyler09/Qwen3-Coder-Next-GPTQ-4bit
```

Qwen3-Coder-Next GPTQ 4-bit

GPTQ 4-bit quantization of Qwen/Qwen3-Coder-Next, an 80B-parameter Mixture-of-Experts (MoE) coding model with 3B activated parameters per token.

Model Overview

Architecture: Qwen3NextForCausalLM (hybrid linear + full attention with DeltaNet)
Total parameters: ~80B
Activated parameters: ~3B per token (10 of 512 experts selected per token)
Layers: 48 (36 linear attention + 12 full attention, repeating 3:1 pattern)
Experts: 512 per layer + 1 shared expert per layer
Context length: 262,144 tokens
Supports: Tool calling, code generation, general chat

Quantization Details

All 73,728 MoE expert modules (512 experts x 3 projections x 48 layers) are quantized to INT4 using GPTQ. Non-expert modules remain at FP16 for quality preservation.

Component	Precision	Notes
MoE experts (`gate_proj`, `up_proj`, `down_proj`)	INT4 (GPTQ)	73,728 modules quantized
Attention (`q_proj`, `k_proj`, `v_proj`, `o_proj`)	FP16	Full precision
Linear attention (`in_proj_qkvz`, `out_proj`, `in_proj_ba`)	FP16	Full precision
Shared experts	FP16	Full precision
Embeddings, LM head, norms	FP16	Full precision

GPTQ configuration:

Bits: 4
Group size: 32
Symmetric: Yes
desc_act: No
true_sequential: Yes
Failsafe: RTN for poorly-calibrated rare experts (7,650 of 73,728 modules, ~10.4%)

Calibration

Dataset: Mixed - evol-codealpaca-v1 (code) + C4 (general text)
Samples: 2,048 with context length binning (uniform distribution across 256-2048 token bins)
Quantizer: GPTQModel v5.7.0

See quantize.py for the full quantization script.

Model Size

Version	Size	Compression
BF16 (original)	~160 GB	-
GPTQ 4-bit	47 GB	3.4x

Perplexity

Evaluated on wikitext-2-raw-v1 (test set), seq_len=2048, stride=512:

Model	Perplexity	Degradation
BF16 (original)	6.9401	-
GPTQ 4-bit	6.9956	+0.8%

Usage

vLLM (Recommended)

vllm serve btbtyler09/Qwen3-Coder-Next-GPTQ-4bit \
  --tensor-parallel-size 4 \
  --trust-remote-code \
  --quantization gptq \
  --max-model-len 32768

Tool Calling

This model supports tool calling via the Qwen3-Coder chat template. The quantized model includes:

chat_template.jinja - Chat template with tool support
qwen3coder_tool_parser_vllm.py - vLLM tool parser plugin
qwen3_coder_detector_sgl.py - SGLang tool detector

For vLLM tool calling:

vllm serve btbtyler09/Qwen3-Coder-Next-GPTQ-4bit \
  --tensor-parallel-size 4 \
  --trust-remote-code \
  --dtype float16 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

Credits

Base Model: Qwen - Qwen3-Coder-Next
Quantization: GPTQ via GPTQModel v5.7.0
Quantized by: btbtyler09

License

This model inherits the Apache 2.0 license from the base model.

Downloads last month: 5,794

Model tree for btbtyler09/Qwen3-Coder-Next-GPTQ-4bit

Base model

Qwen/Qwen3-Coder-Next

Quantized

(101)

this model