Skip to content
AI Atlas
ModelActiveOpen weights

amd/Qwen3-VL-8B-Instruct-w8a8-llmcompressor

AMDhuggingface.co/amd/Qwen3-VL-8B-Instruct-w8a8-llm

Updated 12 min ago · first seen 11 Sept 2026

model_01M294X79KCTC71YFGSCQ7NFFX

Parameters
8.77B
T2 · 21 min ago
Released
3 Aug 2026
T2 · 16 min ago
License
apache-2.0
T2 · 16 min ago

Specification

Release date
3 Aug 2026

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Openness
open-weights

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium

License
apache-2.0

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Architecture
Qwen3VLForConditionalGeneration

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Parameters
8.77B

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium

Languages
en

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Base model
Qwen/Qwen3-VL-8B-Instruct

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

File size
10.6 GB

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Hugging Face repo
amd/Qwen3-VL-8B-Instruct-w8a8-llmcompressor

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium

Pipeline tag
image-text-to-text

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium

Downloads
14,079

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 min agomedium

Likes
0

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 min agomedium

Gated
No

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Last modified
2026-08-07T02:01:41+00:00

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium

Library name
transformers

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Downloads all time
14,186

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 min agomedium

Model type
qwen3_vl

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Tags
transformers, safetensors, qwen3_vl, image-text-to-text, quantized, int8, w8a8, dynamic-quantization, 8-bit, llm-compressor, zendnn, compressed-tensors, amd, cpu-inference, en

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Weights dtype
BF16, I8

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

20

Source tiers

T220

Freshest observation

12 min ago

Conflicts

None