HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Qwen2.5-VL-7B-Instruct-AWQ

Qwen/Qwen2.5-VL-7B-Instruct-AWQ

kind
awq
quant
awq
family
qwen
modality
image-text-to-text
root model
Qwen/Qwen2.5-VL-7B-Instruct
provider
Qwen
license
apache-2.0
language
en
context
32,768
library
transformers
vRAM (GB)
2.5
size on disk
—
downloads
2,748,113
likes
105
created
—
last modified
2025-04-06T16:25:10+00:00 (2025)
huggingface
https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct-AWQ
tags
transformerssafetensorsqwen2_5_vlimage-text-to-textmultimodalconversationalenarxiv:2309.00071arxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:quantized:Qwen/Qwen2.5-VL-7B-Instructlicense:apache-2.0text-generation-inferenceendpoints_compatible4-bitawqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
DocVQAmultimodal96.0high| | 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 |
MMBenchmultimodal87.9high| | 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 |
MathVistamultimodal73.8high| | 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 |

Discussions (10)

titleauthorstatuscommentstype
fix spelling error in read meFlack1open0disc
vllm implementationTahirCopen0disc
AWQ quantization script to Qwen-VL-2.5 7B modelBerkesuleopen0disc
Necessary transformers versionchefexperteopen0disc
lm head in the trained model is not in AWQ formatpooya-mohammadiopen0disc
111132434eeedraft0disc
Is AWQ quantization applied only to the anguage model of this model?sinchir0open0disc
License clarificationValerianGuillotopen0disc
Empty output when using Qwen2.5-VL-7B-Instruct-AWQ example code from READMEWpythonWopen0disc
Add link to paper and codenielsropen0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.