Downloads · 30 days
68
37% of all-time downloads
Mistral-Medium-3.5-128B-GGUF-Q8_0-mmproj
Lockout/Mistral-Medium-3.5-128B-GGUF-Q8_0-mmproj
Mistral-Medium-3.5-128B-GGUF-Q8_0-mmproj is a machine learning model from Lockout. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Since nobody appears to want to post Q80 mmproj and the default is over 5gb in size, it's hard to get all your context into 96gb. Downloading the weights is a nonstarter because they are 200G+
All-time downloads
185
Public
Repo size
2.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf2.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- May 13, 2026
- Updated
- May 14, 2026
- SHA
- 998dabb9
Base models
Model card
From the Hugging Face model README
Since nobody appears to want to post Q8_0 mmproj and the default is over 5gb in size, it's hard to get all your context into 96gb. Downloading the weights is a nonstarter because they are 200G+
All facilities for requantizing mmproj are broken in both ik_llama.cpp and llama.cpp. What do?
Screw around with models and use python! Took a while but now q8_0 mmproj exists and works. Maybe also the script is useful for someone?
- License
- apache-2.0
- Created
- May 13, 2026
- Updated
- May 14, 2026