Instructions to use ucbye/Qwen3-Coder-Next-NVFP4-GB10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ucbye/Qwen3-Coder-Next-NVFP4-GB10 with Transformers:

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

pipe = pipeline("text-generation", model="ucbye/Qwen3-Coder-Next-NVFP4-GB10")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ucbye/Qwen3-Coder-Next-NVFP4-GB10")
model = AutoModelForCausalLM.from_pretrained("ucbye/Qwen3-Coder-Next-NVFP4-GB10")
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 ucbye/Qwen3-Coder-Next-NVFP4-GB10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ucbye/Qwen3-Coder-Next-NVFP4-GB10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ucbye/Qwen3-Coder-Next-NVFP4-GB10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ucbye/Qwen3-Coder-Next-NVFP4-GB10

SGLang

How to use ucbye/Qwen3-Coder-Next-NVFP4-GB10 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 "ucbye/Qwen3-Coder-Next-NVFP4-GB10" \
    --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": "ucbye/Qwen3-Coder-Next-NVFP4-GB10",
		"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 "ucbye/Qwen3-Coder-Next-NVFP4-GB10" \
        --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": "ucbye/Qwen3-Coder-Next-NVFP4-GB10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ucbye/Qwen3-Coder-Next-NVFP4-GB10 with Docker Model Runner:
```
docker model run hf.co/ucbye/Qwen3-Coder-Next-NVFP4-GB10
```

gdubicki/Qwen3-Coder-Next-NVFP4-GB10

Public mirror of saricles/Qwen3-Coder-Next-NVFP4-GB10.

Weights are byte-identical to the upstream quant (config.json and model.safetensors.index.json SHA-256 verified). This mirror exists to provide a pinned, stable, ungated reference for the qwen3-coder-next deployment project on DGX Spark (GB10). Use the upstream repo if you want to track author updates.

Credits

Base model: Qwen/Qwen3-Coder-Next by Alibaba / Qwen team (Apache-2.0)
NVFP4 quantization: saricles using LLM Compressor with LLMCOMPRESSOR_MOE_CALIBRATE_ALL_EXPERTS=1 (all 512 experts calibrated)
Calibration data: HuggingFaceH4/ultrachat_200k (64 samples × 2048 tok)
License: Apache-2.0 (inherited from base model; redistribution permitted)

Model details

Architecture: qwen3_next — Hybrid DeltaNet linear attention + full attention + latent MoE
Layers: 48 total (36 DeltaNet linear-attention, 12 full-attention)
Parameters: 79.7B total, ~3B active per token (512 experts, 10 active + 1 shared)
Quantization: NVFP4 via compressed-tensors; lm_head, embed_tokens, linear_attn layers, mlp.gate, mlp.shared_expert_gate kept in BF16
Size on disk: 45.9 GB (70% reduction from ~149 GB BF16)
KV cache: FP8 (12 full-attention layers only; DeltaNet has no KV cache)
Max context: 262,144 tokens

Verified performance

Measured on DGX Spark (GB10 Blackwell, SM12.1, 128 GB unified LPDDR5X) with vLLM (Marlin NVFP4, FP8 KV cache):

Metric	Value
Throughput (single request)	~61 tok/s
KV cache concurrency @ 262K	~5 concurrent sessions (DeltaNet has no KV cache → 31.65× vs a pure-attention 80B model)

Same decode throughput as Nemotron-3-Nano-30B-A3B-NVFP4 (both 3B active), but with a native 262K context window.

Usage

docker run --rm --runtime=nvidia --gpus all \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e VLLM_NVFP4_GEMM_BACKEND=marlin \
  -e VLLM_TEST_FORCE_FP8_MARLIN=1 \
  -e VLLM_USE_FLASHINFER_MOE_FP4=0 \
  -e VLLM_MARLIN_USE_ATOMIC_ADD=1 \
  vllm/vllm-openai:cu130-nightly \
  gdubicki/Qwen3-Coder-Next-NVFP4-GB10 \
  --dtype auto \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.90 \
  --max-model-len 262144 \
  --attention-backend flashinfer \
  --tool-call-parser qwen3_coder \
  --enable-chunked-prefill \
  --enable-prefix-caching

Full deployment scripts: https://github.com/grzegorzdubicki-ai/qwen3-coder-next

Downloads last month: 226

Model tree for ucbye/Qwen3-Coder-Next-NVFP4-GB10

Base model

Qwen/Qwen3-Coder-Next

Quantized

saricles/Qwen3-Coder-Next-NVFP4-GB10

Quantized

(2)

this model