Mellum2-12B-A2.5B-Instruct-GGUF

Home/Models/Mungert/Mellum2-12B-A2.5B-Instruct-GGUF

Mungert/Mellum2-12B-A2.5B-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: text-generation
root model: JetBrains/Mellum2-12B-A2.5B-Instruct
provider: Mungert
license: apache-2.0
language: en
context: 131,072
library: transformers
vRAM (GB): —
size on disk: —
downloads: 478
likes: 0
created: —
last modified: 2026-06-13T05:24:18+00:00 (2026)
huggingface: https://huggingface.co/Mungert/Mellum2-12B-A2.5B-Instruct-GGUF
tags: transformersgguftext-generationenarxiv:2605.31268license:apache-2.0model-indexendpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
MMLU	knowledge	77.4	MMLU-Redux	medium	`\| MMLU-Redux \| 77.4 \| 78.1 \| 87.5 \| 91.1 \| 71.8 \| 85.9 \| 38.1 \|`
EvalPlus	coding	76.2	EvalPlus	medium	`\| EvalPlus \| 76.2 \| 78.4 \| 69.4 \| 71.8 \| 67.3 \| 74.1 \| 73.8 \|`
IFEval	instruction-following	69.3	IFEval	medium	`\| IFEval \| 69.3 \| 75.8 \| 82.1 \| 83.9 \| 83.2 \| 67.3 \| 56.2 \|`
BFCL (function calling)	agentic	43.1	BFCL v3	medium	`\| BFCL v3 \| 43.1 \| 66.3 \| 64.1 \| 70.5 \| 41.9 \| 52.7 \| — \|`
GPQA Diamond	reasoning	38.9	GPQA Diamond	medium	`\| GPQA Diamond \| 38.9 \| 40.9 \| 76.8 \| 79.8 \| 40.9 \| 58.6 \| 20.2 \|`
BFCL (function calling)	agentic	31.8	BFCL v4	medium	`\| BFCL v4 \| 31.8 \| 44.2 \| 52.0 \| 60.6 \| 19.8 \| 38.8 \| — \|`
LiveCodeBench	coding	30.9	LiveCodeBench v6	medium	`\| LiveCodeBench v6 \| 30.9 \| 37.2 \| 51.0 \| 63.7 \| 28.2 \| 42.4 \| 28.1 \|`

none scraped.