Qwen2.5-VL-72B-Instruct-AWQ

Home/Models/Qwen/Qwen2.5-VL-72B-Instruct-AWQ

Qwen/Qwen2.5-VL-72B-Instruct-AWQ

kind: awq
quant: awq
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2.5-VL-72B-Instruct
provider: Qwen
license: —
language: —
context: 32,768
library: —
vRAM (GB): 2.5
size on disk: —
downloads: 299,010
likes: 73
created: —
last modified: 2025-03-07T10:21:14+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct-AWQ
tags: transformerssafetensorsqwen2_5_vlimage-text-to-textmultimodalconversationalenarxiv:2309.00071arxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2.5-VL-72B-Instructbase_model:quantized:Qwen/Qwen2.5-VL-72B-Instructlicense:othertext-generation-inferenceendpoints_compatible4-bitawqregion:us

benchmark	category	score	conf	evidence
DocVQA	multimodal	96.1	high	`\| Qwen2.5-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) \| 70.0 \| 96.1 \| 88`
MMBench	multimodal	88.2	high	`\| Qwen2.5-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) \| 70.0 \| 96.1 \| 88`
MathVista	multimodal	75.3	high	`\| Qwen2.5-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2.5-VL-72B-Instruct)) \| 70.0 \| 96.1 \| 88`

none scraped.