Downloads · 30 days
128
8% of all-time downloads
Huihui-Qwen3-VL-8B-Instruct-abliterated-AWQ-int4
quant-mind/Huihui-Qwen3-VL-8B-Instruct-abliterated-AWQ-int4
Huihui-Qwen3-VL-8B-Instruct-abliterated-AWQ-int4 is a image-text-to-text model from quant-mind. 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.
Quantização AWQ int4 (W4A16) de huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated, produzida com llm-compressor.
All-time downloads
1.6K
Public
Parameters
9B
7.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
Parameter types
How the weights are stored.
I326.9B · 77%
Try a prompt
Base models
Model card
From the Hugging Face model README
Huihui-Qwen3-VL-8B-Instruct-abliterated-AWQ-int4
Quantização AWQ int4 (W4A16) de huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated,
produzida com llm-compressor.
Configuração (ajustada para máxima precisão)
- Esquema: W4A16 (pesos int4 simétricos por grupo, ativações em 16-bit)
group_size: 32- Amostras de calibração: 512 (lmms-lab/flickr30k)
max_seq_length: 2048duo_scaling: False- Mantidos em bf16 (não quantizados): torre de visão (
visual.*) elm_head
Uso com vLLM
vllm serve quant-mind/Huihui-Qwen3-VL-8B-Instruct-abliterated-AWQ-int4 --quantization compressed-tensors --max-model-len 8192
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026