Downloads · 30 days
187
3% of all-time downloads
Qwopus3.6-27B-v1-preview-MTP-GGUF
noctrex/Qwopus3.6-27B-v1-preview-MTP-GGUF
Qwopus3.6-27B-v1-preview-MTP-GGUF is a image-text-to-text model from noctrex. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
These are quantizations of the model Jackrong / Qwopus3.6-27B-v1-preview I've added the MTP layer on it. My personal speed improvement on my 7900XTX with the vulkan backend has been from ~40 tps to around ~60 tps. An…
All-time downloads
6.7K
Public
Repo size
140 GB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.gguf140 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 21, 2026
- SHA
- 1df30620
Try a prompt
Base models
Model card
From the Hugging Face model README
These are quantizations of the model Jackrong / Qwopus3.6-27B-v1-preview
I've added the MTP layer on it.
My personal speed improvement on my 7900XTX with the vulkan backend has been from ~40 tps to around ~60 tps.
An imatrix has been calulated for coding tasks, as such it is specialized for coding.
Quick Start
- Download the latest release of llama.cpp.
- Download your preferred model variant from below.
- Task
- Image-Text-to-Text
- Created
- May 16, 2026
- Updated
- May 21, 2026