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

Home/Models/Mungert/Qwen2.5-VL-3B-Instruct-GGUF

Mungert/Qwen2.5-VL-3B-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2.5-VL-3B-Instruct
provider: Mungert
license: —
language: —
context: 32,768
library: —
vRAM (GB): —
size on disk: —
downloads: 6,539
likes: 29
created: —
last modified: 2025-09-24T15:41:41+00:00 (2025)
huggingface: https://huggingface.co/Mungert/Qwen2.5-VL-3B-Instruct-GGUF
tags: transformersggufmultimodalimage-text-to-textenarxiv:2309.00071arxiv:2409.12191arxiv:2308.12966endpoints_compatibleregion:usimatrixconversational

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	91.6	DocVQA<sub>test</sub>	medium	`\| DocVQA<sub>test</sub> \| 91.6 \| 94.5 \| 93.9 \|`
MMBench	multimodal	79.3	MMBench-V1.1<sub>test</sub>	medium	`\| MMBench-V1.1<sub>test</sub> \| 79.3 \| 80.7 \| 77.6 \|`
MathVista	multimodal	60.5	MathVista<sub>testmini</sub>	medium	`\| MathVista<sub>testmini</sub> \| 60.5 \| 58.2 \| 62.3 \|`
MMMU	multimodal	52.3	MMMU<sub>val</sub>	medium	`\| MMMU<sub>val</sub> \| 52.3 \| 54.1 \| 53.1 \|`
MMMU	multimodal	32.7	MMMU-Pro<sub>val</sub>	medium	`\| MMMU-Pro<sub>val</sub> \| 32.7 \| 30.5 \| 31.6 \|`
MMBench	multimodal	1.73	MMBench-Video	medium	`\| MMBench-Video \| 1.73 \| 1.44 \| 1.63 \|`

none scraped.