Phi-3-vision-128k-instruct

Home/Models/microsoft/Phi-3-vision-128k-instruct

microsoft/Phi-3-vision-128k-instruct

kind: original
quant: bf16 (16-bit)
family: phi
modality: text-generation
root model: microsoft/Phi-3-vision-128k-instruct
provider: microsoft
license: mit
language: multilingual
context: 128K
library: —
vRAM (GB): —
size on disk: —
downloads: 245,392
likes: 973
created: —
last modified: 2025-12-10T20:23:49+00:00 (2025)
huggingface: https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
tags: transformerssafetensorsphi3_vtext-generationnlpcodevisionconversationalcustom_codemultilinguallicense:mitregion:us

benchmark	category	score	context	conf	evidence
ChartQA	multimodal	81.4	ChartQA	medium	`\| ChartQA \| 81.4 \| 55.0 \| 50.9 \| 65.8 \| 59.3 \| 58.0 \| 62.3 \|`
MMBench	multimodal	80.5	MMBench	medium	`\| MMBench \| 80.5 \| 76.3 \| 75.8 \| 79.4 \| 62.4 \| 80.0 \| 86.1 \|`
MathVista	multimodal	44.5	MathVista	medium	`\| MathVista \| 44.5 \| 31.5 \| 29.4 \| 34.8 \| 33.2 \| 35.0 \| 47.5 \|`
MMMU	multimodal	40.4	MMMU	medium	`\| MMMU \| 40.4 \| 34.2 \| 39.0 \| 36.4 \| 40.7 \| 42.0 \| 55.5 \|`

none scraped.