Mistral-Small-3.2-24B-Instruct-2506-FP8

Home/Models/unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8

Mistral-Small-3.2-24B-Instruct-2506-FP8

unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8

kind: fp8
quant: fp8 (8-bit)
family: mistral
modality: image-text-to-text
root model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
provider: unsloth
license: apache-2.0
language: en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa
context: 128K
library: vllm
vRAM (GB): —
size on disk: —
downloads: 74
likes: 6
created: —
last modified: 2025-06-21T14:16:53+00:00 (2025)
huggingface: https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8
tags: vllmimage-text-to-textenfrdeesptitjakoruzharfaidmsneplrosrsvtrukvi

Benchmark scores (14)

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	94.08		low	`\| Small 3.1 24B Instruct \| 64.00% \| 68.91% \| 86.24% \| 94.08% \| 93.72% \|`
HumanEval	coding	88.99	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
ChartQA	multimodal	86.24		low	`\| Small 3.1 24B Instruct \| 64.00% \| 68.91% \| 86.24% \| 94.08% \| 93.72% \|`
MMLU	knowledge	80.62	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
MBPP	coding	74.63	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
MATH	math	69.3	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
MathVista	multimodal	68.91		low	`\| Small 3.1 24B Instruct \| 64.00% \| 68.91% \| 86.24% \| 94.08% \| 93.72% \|`
MMLU-Pro	knowledge	66.76	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
MMMU	multimodal	64.0		low	`\| Small 3.1 24B Instruct \| 64.00% \| 68.91% \| 86.24% \| 94.08% \| 93.72% \|`
WildBench	chat	55.6		low	`\| Small 3.1 24B Instruct \| 55.6% \| 19.56% \| 82.75% \|`
GPQA Diamond	reasoning	45.96	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
GPQA	reasoning	44.42	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`
Chatbot Arena	chat	19.56		low	`\| Small 3.1 24B Instruct \| 55.6% \| 19.56% \| 82.75% \|`
SimpleQA	knowledge	10.43	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT) \| GPQA Diamond (5-shot CoT )	low	`\| Small 3.1 24B Instruct \| 80.62% \| 66.76% \| 69.30% \| 44.42% \| 45.96% \| 74.63% \| 88.99% \| 10.43% \|`

Discussions (0)

none scraped.