Qwen2.5-VL-3B-Instruct-AWQ

Home/Models/Qwen/Qwen2.5-VL-3B-Instruct-AWQ

Qwen/Qwen2.5-VL-3B-Instruct-AWQ

kind: awq
quant: awq
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2.5-VL-3B-Instruct
provider: Qwen
license: —
language: —
context: 32,768
library: —
vRAM (GB): 2.5
size on disk: —
downloads: 351,921
likes: 64
created: —
last modified: 2025-04-06T16:24:35+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct-AWQ
tags: transformerssafetensorsqwen2_5_vlimage-text-to-textmultimodalconversationalenarxiv:2309.00071arxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:quantized:Qwen/Qwen2.5-VL-3B-Instructtext-generation-inferenceendpoints_compatible4-bitawqregion:us

benchmark	category	score	conf	evidence
DocVQA	multimodal	96.0	high	`\| \| AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) \| 69.1 \| 96.0 \| 87.9 \| 73.8 \|`
MMBench	multimodal	87.9	high	`\| \| AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) \| 69.1 \| 96.0 \| 87.9 \| 73.8 \|`
MathVista	multimodal	73.8	high	`\| \| AWQ<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct-AWQ)) \| 69.1 \| 96.0 \| 87.9 \| 73.8 \|`

none scraped.