Downloads · 30 days
140
2% of all-time downloads
Qwen3-Next-80B-A3B-Thinking-NVFP4
RESMP-DEV/Qwen3-Next-80B-A3B-Thinking-NVFP4
Qwen3-Next-80B-A3B-Thinking-NVFP4 is a text generation model from RESMP-DEV. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Quantized version of Qwen/Qwen3-Next-80B-A3B-Thinking using LLM Compressor and the NVFP4 (E2M1 + E4M3) format.
All-time downloads
6.4K
Public
Repo size
47.6 GB
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors47.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_next
- Access
- Public
- Created
- Oct 11, 2025
- Updated
- Oct 11, 2025
- SHA
- 6a5a817c
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-Next-80B-A3B-Thinking-NVFP4
Quantized version of Qwen/Qwen3-Next-80B-A3B-Thinking using LLM Compressor and the NVFP4 (E2M1 + E4M3) format.
This time it actually works! We think
This should be the start of a new series of hopefully optimal NVFP4 quantizations as capable cards continue to grow out in the wild.
Model Summary
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3-Next-80B-A3B-Thinking |
| Quantization | NVFP4 (FP4 microscaling, block = 16, scale = E4M3) |
| Method | Post-Training Quantization with LLM Compressor |
| Toolchain | LLM Compressor |
| Hardware target | NVIDIA Blackwell (Untested on RTX cards) / GB200 Tensor Cores |
| Precision | Weights & activations = FP4 • Scales = FP8 (E4M3) |
| Maintainer | RESMP.DEV |
Description
This model is a drop-in replacement for Qwen/Qwen3-Next-80B-A3B-Thinking that runs in NVFP4 precision. Accuracy remains within ≈ 1 % of the FP8 baseline on standard reasoning and coding benchmarks.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_next
- License
- apache-2.0
- Languages
- en, zh
- Created
- Oct 11, 2025
- Updated
- Oct 11, 2025