Download

bash
Copy code
hf download lyf/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 \
  --local-dir ./qwen36-35b-a3b-hauhaucs-nvfp4

vLLM quickstart

bash
Copy code
VLLM_NVFP4_GEMM_BACKEND=marlin \
vllm serve lyf/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 \
  --served-model-name qwen36-35b-a3b-hauhaucs-nvfp4 \
  --quantization compressed-tensors \
  --kv-cache-dtype fp8 \
  --max-model-len 131072 \
  --max-num-seqs 1 \
  --max-num-batched-tokens 4096 \
  --gpu-memory-utilization 0.90 \
  --enable-prefix-caching \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3 \
  --trust-remote-code

Local path quickstart:

bash
Copy code
hf download lyf/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-NVFP4 \
  --local-dir ./qwen36-35b-a3b-hauhaucs-nvfp4

VLLM_NVFP4_GEMM_BACKEND=marlin \
vllm serve ./qwen36-35b-a3b-hauhaucs-nvfp4 \
  --served-model-name qwen36-35b-a3b-hauhaucs-nvfp4 \
  --quantization compressed-tensors \
  --kv-cache-dtype fp8 \
  --max-model-len 131072 \
  --max-num-seqs 1 \
  --max-num-batched-tokens 4096 \
  --gpu-memory-utilization 0.90 \
  --enable-prefix-caching \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3 \
  --trust-remote-code

Quantization recipe

python
Copy code
recipe = QuantizationModifier(
    targets="Linear", scheme="NVFP4",
    ignore=["lm_head", "re:.*visual.*", "re:.*mlp.gate$",
            "re:.*mlp.shared_expert_gate$", "re:.*linear_attn.*", "re:^mtp.*"],
)
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=1024,
    num_calibration_samples=128,
    moe_calibrate_all_experts=True,
    pipeline="basic",
)

• Calibration: HuggingFaceH4/ultrachat_200k, 128 samples x 1024 tokens
• MTP tensors copied from Qwen/Qwen3.6-35B-A3B
• Converted using li-yifei/gguf-to-nvfp4

Pipeline:

text
Copy code
Q8_K_P GGUF -> step1_convert_qwen36_moe.py -> HF bf16 -> step2_quantize_qwen36_moe.py -> NVFP4

Source models

• Uncensored source: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
• Original base: Qwen/Qwen3.6-35B-A3B

Acknowledgments

• HauhauCS for the uncensored GGUF source
• Qwen for the base model and MTP weights
• AEON-7 and RedHatAI for conservative quantization approach reference