Nanbeige4.1-3B-GGUF

Home/Models/Mungert/Nanbeige4.1-3B-GGUF

Mungert/Nanbeige4.1-3B-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: text-generation
root model: Nanbeige/Nanbeige4-3B-Base
provider: Mungert
license: apache-2.0
language: en, zh
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 458
likes: 1
created: —
last modified: 2026-02-15T20:45:10+00:00 (2026)
huggingface: https://huggingface.co/Mungert/Nanbeige4.1-3B-GGUF
tags: transformersggufllmnanbeigetext-generationenzhbase_model:Nanbeige/Nanbeige4-3B-Basebase_model:quantized:Nanbeige/Nanbeige4-3B-Baselicense:apache-2.0endpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
AIME 2026	math	81.46	AIME 2026 I	medium	`\| AIME 2026 I \| 81.46 \| 70.42 \| 76.46 \| 75.83 \| <u>87.30<u> \| 84.1 \| 87.40 \|`
GPQA	reasoning	65.8	GPQA	medium	`\| GPQA \| 65.8 \| 62.0 \| 63.38 \| 68.4 \| 73.4 \| <u>82.2<u> \| 83.8 \|`
BFCL (function calling)	agentic	44.87	BFCL-V4	medium	`\| BFCL-V4 \| 44.87 \| 42.20 \| 45.14 \| 47.90 \| 48.6 \| <u>53.8<u> \| 56.50 \|`
Chatbot Arena	chat	34.9	Arena-Hard-v2	medium	`\| Arena-Hard-v2 \| 34.9 \| 26.3 \| 36.9 \| 56.0 \| <u>60.2<u> \| 60.0 \| 73.2 \|`
Humanity's Last Exam	knowledge	21.5		low	`\| MiroThinker-v1.0-8B \| 61 \| – \| 31.1 \| 40.2 \| 66.4 \| 21.5 \| 40.4 \|`
Humanity's Last Exam	knowledge	6.72	HLE (Text-only)	medium	`\| HLE (Text-only) \| 6.72 \| 5.28 \| 7.00 \| 9.31 \| <u>11.77<u> \| 10.98 \| 12.60 \|`

none scraped.