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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

GadflyII commited on Feb 4

Commit

f75ee39

verified ·

1 Parent(s): 162c8fd

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -27

README.md CHANGED Viewed

@@ -12,6 +12,9 @@ license: apache-2.0
 pipeline_tag: text-generation
 ---
 # Qwen3-Coder-Next-NVFP4
 NVFP4 quantized version of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) (80B-A3B).
@@ -32,7 +35,7 @@ NVFP4 quantized version of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Q
 ## Quantization Details
-Quantized using [llmcompressor](https://github.com/vllm-project/llm-compressor) 0.9.0.1 following RedHatAI's approach.
 ```python
 NUM_CALIBRATION_SAMPLES = 20
@@ -60,43 +63,20 @@ ignore = [
 ### Context Length Testing
-Successfully tested up to **128K tokens** with FP8 KV cache (~95GB VRAM per GPU).
 ## Usage with vLLM
-Requires vLLM with NVFP4 support (0.16.0+).
 ```bash
-# Standard serving (TP=2)
-vllm serve GadflyII/Qwen3-Coder-Next-NVFP4 \
-    --tensor-parallel-size 2 \
-    --max-model-len 49152
-# Extended context (128K with FP8 KV cache)
 vllm serve GadflyII/Qwen3-Coder-Next-NVFP4 \
     --tensor-parallel-size 2 \
     --max-model-len 131072 \
     --kv-cache-dtype fp8
-# Expert Parallelism (alternative to TP)
-vllm serve GadflyII/Qwen3-Coder-Next-NVFP4 \
-    --tensor-parallel-size 1 \
-    --expert-parallel-size 2 \
-    --max-model-len 131072 \
-    --kv-cache-dtype fp8
 ```
-### Notes for Blackwell GPUs (SM120)
-- First startup may take longer due to CUDA graph compilation
-- SymmMemCommunicator not supported on device capability 12.0 (handled automatically)
-- Some CUTLASS TMA WS grouped gemm tactics may fail during autotuning (non-fatal)
-## Hardware Requirements
-- **Minimum**: 2x 48GB GPUs (for inference at shorter context)
-- **Recommended**: 2x 96GB GPUs (for 128K context with FP8 KV cache)
 ## License
 Apache 2.0 (same as base model)

 pipeline_tag: text-generation
 ---
+# Note: If you have a multi-GPU SM120 Blackwell system (RTX 50/Pro), try my vLLM fork to resolve P2P / TP=2 issues (Pending PR into upstream).
+https://github.com/Gadflyii/vllm/tree/main
 # Qwen3-Coder-Next-NVFP4
 NVFP4 quantized version of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) (80B-A3B).
 ## Quantization Details
+Quantized using [llmcompressor](https://github.com/vllm-project/llm-compressor) 0.9.0.1.
 ```python
 NUM_CALIBRATION_SAMPLES = 20
 ### Context Length Testing
+Successfully tested up to **128K tokens** with FP8 KV cache (Not enough VRAM to test any higher context).
 ## Usage with vLLM
+Requires vLLM with NVFP4 support (0.16.0+), Transformers 5.0.0+
 ```bash
+#vllm Serving
 vllm serve GadflyII/Qwen3-Coder-Next-NVFP4 \
     --tensor-parallel-size 2 \
     --max-model-len 131072 \
     --kv-cache-dtype fp8
 ```
 ## License
 Apache 2.0 (same as base model)