Kimi-VL-A3B-Thinking

Home/Models/moonshotai/Kimi-VL-A3B-Thinking

moonshotai/Kimi-VL-A3B-Thinking

kind: original
quant: bf16 (16-bit)
family: kimi
modality: image-text-to-text
root model: moonshotai/Kimi-VL-A3B-Instruct
provider: moonshotai
license: mit
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 162,056
likes: 450
created: —
last modified: 2026-01-30T04:52:57+00:00 (2026)
huggingface: https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking
tags: transformerssafetensorskimi_vlfeature-extractionimage-text-to-textconversationalcustom_codearxiv:2504.07491base_model:moonshotai/Kimi-VL-A3B-Instructbase_model:finetune:moonshotai/Kimi-VL-A3B-Instructlicense:mitregion:us

benchmark	category	score	context	conf	evidence
MMMU	multimodal	69.1	MMMU (val) (Pass@1)	medium	`\| MMMU (val) (Pass@1) \| 69.1 \| 60.0 \| 74.8 \| 58.6 \| 64.8 \| 59.6 \| 77.3 \| 70.3 \| 70.0 \| 61.7 \|`
MathVista	multimodal	63.8	MathVista (mini) (Pass@1)	medium	`\| MathVista (mini) (Pass@1) \| 63.8 \| 56.7 \| 74.8 \| 68.2 \| 62.3 \| 56.4 \| 71.0 \| 71.4 \| 74.9 \| 71.3 \|`

none scraped.