Downloads · 30 days
19
12% of all-time downloads
Qwen3.8-27B-ARA-vision-MTP
cfigueiroa/Qwen3.8-27B-ARA-vision-MTP
Qwen3.8-27B-ARA-vision-MTP is a image-text-to-text model from cfigueiroa. 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 transformers. The card lists the license as apache-2.0.
Cérebro de cygnal/Qwen3.8-27B-heretic-ara-Q4KM-MTP-GGUF: uma passada ARA do trohrbaugh já com NextN dentro, mais o projector de visão oficial do ggml-org.
All-time downloads
163
Public
Repo size
17.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf17.4 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026
- SHA
- c0ddf46d
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B ARA (1 passada) + visão + MTP
Cérebro de cygnal/Qwen3.8-27B-heretic-ara-Q4_K_M-MTP-GGUF: uma passada ARA do trohrbaugh já com NextN dentro, mais o projector de visão oficial do ggml-org.
Menos abliterado que o RVN (3 passadas). Útil para A/B contra o repo irmão cfigueiroa/Qwen3.8-27B-RVN-vision-MTP.
Ficheiros
| ficheiro | o que é |
|---|---|
Qwen3.8-27B-heretic-ara-Q4_K_M-MTP.gguf | texto 1× ARA Q4_K_M com NextN 15/15 (~16.8 GB) |
mmproj-Qwen3.8-27B-Q8_0.gguf | visão oficial ggml-org |
Não uses -md. O acelerador já está no principal.
Correr
llama-server \
-m Qwen3.8-27B-heretic-ara-Q4_K_M-MTP.gguf \
--mmproj mmproj-Qwen3.8-27B-Q8_0.gguf \
--jinja --reasoning off --device CUDA0
Apache-2.0. Não afiliado a Qwen, trohrbaugh ou cygnal.
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026