Skip to content

malaiwah

Qwen3.8-27B-EXL3-S16-V-research

malaiwah/Qwen3.8-27B-EXL3-S16-V-research

Qwen3.8-27B-EXL3-S16-V-research is a image-text-to-text model from malaiwah. 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 vllm. The card lists the license as apache-2.0.

This build was measured and rejected, and here is by how much. On shard 0 of the v5 held-out suite — 512 contexts, 1,048,064 scored positions, 330 source clusters, one shared BF16 head, one shared BF16 reference — it…

Downloads · 30 days

19

15% of all-time downloads

All-time downloads

124

Public

Parameters

6.9B

13.7 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors13.7 GB · 100%

Parameter types

How the weights are stored.

I165.1B · 74%

Try a prompt

Base models

Task
Image-Text-to-Text
Library
vllm
Type
qwen3_5
License
apache-2.0
Created
Aug 16, 2026
Updated
Aug 20, 2026