Downloads · 30 days
9
3% of all-time downloads
severian-vision-gguf
tmancino/severian-vision-gguf
severian-vision-gguf is a image-text-to-text model from tmancino. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
Deployment-ready GGUF for the TE NIMS multimodal vision sidecar.
All-time downloads
338
Public
Repo size
5.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.3 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- May 18, 2026
- Updated
- May 18, 2026
- SHA
- a1034acf
Try a prompt
Model card
From the Hugging Face model README
Severian Vision GGUF
Deployment-ready GGUF for the TE NIMS multimodal vision sidecar.
What this repo is
This repo contains the quantized vision model used by the TE NIMS demo's
llama-server sidecar. It is not sufficient by itself: the matching mmproj
artifact is also required at runtime.
Required companion repo
tmancino/severian-vision-mmproj
You need both:
severian-vision-q4_k_m.ggufmmproj-severian-vision.gguf
Runtime use
The public demo serves this model as:
- Runtime name:
severian-vision - Intended runtime:
llama-server/llama.cpp
The GCP/systemd deployment points llama-server at this file and the matching
mmproj file.
Files
severian-vision-q4_k_m.ggufSHA256SUMS
Notes
- This is the deployable vision inference artifact.
- It should be versioned in lockstep with the matching projector repo.
- Task
- Image-Text-to-Text
- Library
- gguf
- License
- apache-2.0
- Created
- May 18, 2026
- Updated
- May 18, 2026