MiniMax-M2-GGUF

Home/Models/unsloth/MiniMax-M2-GGUF

MiniMax-M2-GGUF

unsloth/MiniMax-M2-GGUF

kind: gguf
quant: gguf (16-bit)
family: minimax
modality: text-generation
root model: MiniMaxAI/MiniMax-M2
provider: unsloth
license: mit
language: —
context: 100m
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,723
likes: 89
created: —
last modified: 2025-11-03T09:39:50+00:00 (2025)
huggingface: https://huggingface.co/unsloth/MiniMax-M2-GGUF
tags: transformersggufminimaxunslothtext-generationarxiv:2504.07164arxiv:2509.06501arxiv:2509.13160base_model:MiniMaxAI/MiniMax-M2base_model:quantized:MiniMaxAI/MiniMax-M2license:mitendpoints_compatibleregion:usimatrixconversational

Benchmark scores (13)

benchmark	category	score	context	conf	evidence
LiveCodeBench	coding	83.0	LiveCodeBench (LCB)	medium	`\| LiveCodeBench (LCB) \| 83 \| 66 \| 71 \| 80 \| 85 \| 70 \| 61 \| 79 \|`
MMLU-Pro	knowledge	82.0	MMLU-Pro	medium	`\| MMLU-Pro \| 82 \| 84 \| 88 \| 86 \| 87 \| 83 \| 82 \| 85 \|`
AIME 2025	math	78.0	AIME25	medium	`\| AIME25 \| 78 \| 74 \| 88 \| 88 \| 94 \| 86 \| 57 \| 88 \|`
GPQA Diamond	reasoning	78.0	GPQA-Diamond	medium	`\| GPQA-Diamond \| 78 \| 78 \| 83 \| 84 \| 85 \| 78 \| 77 \| 80 \|`
IFBench	instruction-following	72.0	IFBench	medium	`\| IFBench \| 72 \| 55 \| 57 \| 49 \| 73 \| 43 \| 42 \| 54 \|`
SWE-bench Verified	swe	69.4	SWE-bench Verified	medium	`\| SWE-bench Verified \| 69.4 \| 72.7 * \| 77.2 * \| 63.8 * \| 74.9 * \| 68 * \| 69.2 * \| 67.8 * \|`
BrowseComp	agentic	48.5	BrowseComp-zh	medium	`\| BrowseComp-zh \| 48.5 \| 29.1 \| 40.8 \| 32.2 \| 65 \| 49.5 \| 28.8 \| 47.9* \|`
Terminal-Bench	agentic-coding	46.3	Terminal-Bench	medium	`\| Terminal-Bench \| 46.3 \| 36.4 * \| 50 * \| 25.3 * \| 43.8 * \| 40.5 * \| 44.5 * \| 37.7 * \|`
BrowseComp	agentic	44.0	BrowseComp	medium	`\| BrowseComp \| 44 \| 12.2 \| 19.6 \| 9.9 \| 54.9* \| 45.1* \| 14.1 \| 40.1* \|`
SciCode	coding	36.0	SciCode	medium	`\| SciCode \| 36 \| 40 \| 45 \| 43 \| 43 \| 38 \| 31 \| 38 \|`
Humanity's Last Exam	knowledge	31.8	HLE (w/ tools)	medium	`\| HLE (w/ tools) \| 31.8 \| 20.3 \| 24.5 \| 28.4 * \| 35.2 * \| 30.4 * \| 26.9 * \| 27.2 * \|`
Terminal-Bench	agentic-coding	24.0	Terminal-Bench-Hard	medium	`\| Terminal-Bench-Hard \| 24 \| 30 \| 33 \| 25 \| 31 \| 23 \| 23 \| 29 \|`
Humanity's Last Exam	knowledge	12.5	HLE (w/o tools)	medium	`\| HLE (w/o tools) \| 12.5 \| 9.6 \| 17.3 \| 21.1 \| 26.5 \| 13.3 \| 6.3 \| 13.8 \|`

Discussions (0)

none scraped.