Downloads · 30 days
249
1% of all-time downloads
Qwen3-Coder-Next-MXFP4_MOE-GGUF
noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
Qwen3-Coder-Next-MXFP4_MOE-GGUF is a text generation model from noctrex. Use it when you need the model to write or continue text.
This is a MXFP4MOE quantization of the model Qwen3-Coder-Next
All-time downloads
25.1K
Public
Repo size
91.8 GB
Likes
21
Public
Repo makeup
Click a slice to open those files.
.gguf91.8 GB · 100%
At a glance
- Task
- Text Generation
- Access
- Public
- Created
- Feb 3, 2026
- Updated
- Feb 19, 2026
- SHA
- 8d2943dd
Try a prompt
Base models
Model card
From the Hugging Face model README
This is a MXFP4_MOE quantization of the model Qwen3-Coder-Next
The suggested parameters from the official docs are:
temperature=1.0
top_p=0.95
top_k=40
As of 2026-02-17 I have updated the model to a MXFP4 quant of higher quality.
The mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest.
So I created 2 new variants, where the other tensors are either BF16 or FP16 instead of Q8.
The order of preference is BF16, then F16.
On some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized.
- Task
- Text Generation
- Created
- Feb 3, 2026
- Updated
- Feb 19, 2026