Downloads · 30 days
23
2% of all-time downloads
GLM-4.7-Flash-MXFP4
xrist0bg/GLM-4.7-Flash-MXFP4
GLM-4.7-Flash-MXFP4 is a machine learning model from xrist0bg. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
994
Public
Repo size
19 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf19 GB · 100%
At a glance
- Access
- Public
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026
- SHA
- 1909e1c2
Base models
Model card
From the Hugging Face model README
llama.cpp version: b7802
Quantization command:
./build/bin/llama-quantize \
--token-embedding-type f16 \
--output-tensor-type f16 \
--tensor-type ".*attn.*=F16" \
--tensor-type ".*norm.*=F32" \
--tensor-type ".*bias=F16" \
--tensor-type ".*shexp.*=F16" \
GLM-4.7-Flash-F16.gguf \
GLM-4.7-Flash-MXFP4.gguf \
MXFP4_MOE
i changed the moe experts (other than the shared expert) to mxfp4 and the dense layer to q8 and keep everything else the same as original for best quality
i can load only around 45k context on 3090 with this config tho
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026