Downloads · 30 days
14
50% of all-time downloads
qwen3-coder-480b-folded-nvfp4-inputscale
Soroosh-Sa/qwen3-coder-480b-folded-nvfp4-inputscale
qwen3-coder-480b-folded-nvfp4-inputscale is a machine learning model from Soroosh-Sa. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This checkpoint was created from folded BF16 weights using a streaming tensor-wise NVFP4 converter.
All-time downloads
28
Public
Parameters
241B
546 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors273 GB · 100%
Parameter types
How the weights are stored.
U8239B · 88%
Model card
From the Hugging Face model README
Qwen3-Coder-480B-A35B Folded NVFP4 Checkpoint
This checkpoint was created from folded BF16 weights using a streaming tensor-wise NVFP4 converter.
Pipeline:
- RMSNorm gamma folded into q/k/v and MLP gate/up-related weights.
- Tensor-wise NVFP4 quantization using the official NVIDIA NVFP4 checkpoint as a layout template.
- Fused QKV/gate-up weight_scale_2 groups normalized for TensorRT-LLM loading.
- input_scale adjusted using original RMSNorm gamma statistics.
Validated:
- Safetensors layout validation passed.
- TensorRT-LLM PyTorch backend loads.
- Smoke generation works on 8x GPUs.
Recommended runtime:
- TensorRT-LLM 1.3.0rc16
- transformers 5.5.4
- TP_SIZE=8
- Type
- qwen3_moe
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026