OpenThinker3-7B-GGUF

Home/Models/Mungert/OpenThinker3-7B-GGUF

Mungert/OpenThinker3-7B-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: text-generation
root model: Qwen/Qwen2.5-7B-Instruct
provider: Mungert
license: apache-2.0
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 353
likes: 0
created: —
last modified: 2025-09-24T15:42:50+00:00 (2025)
huggingface: https://huggingface.co/Mungert/OpenThinker3-7B-GGUF
tags: transformersggufllama-factoryfullgenerated_from_trainertext-generationdataset:open-thoughts/OpenThoughts3-1.2Marxiv:2506.04178base_model:Qwen/Qwen2.5-7B-Instructbase_model:quantized:Qwen/Qwen2.5-7B-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational

benchmark	category	score	conf	evidence
MATH-500	math	82.8	low	`\| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) \| ✅ \| 30.7 \| 22.0 \| 72.5 \| 82.8 \| 15.7 \| 26.1 \| 11.1 \| 14.9 \| 38.6 \| 45.3 \|`
GPQA	reasoning	38.6	low	`\| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) \| ✅ \| 30.7 \| 22.0 \| 72.5 \| 82.8 \| 15.7 \| 26.1 \| 11.1 \| 14.9 \| 38.6 \| 45.3 \|`
AIME 2024	math	30.7	low	`\| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) \| ✅ \| 30.7 \| 22.0 \| 72.5 \| 82.8 \| 15.7 \| 26.1 \| 11.1 \| 14.9 \| 38.6 \| 45.3 \|`
AIME 2025	math	22.0	low	`\| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) \| ✅ \| 30.7 \| 22.0 \| 72.5 \| 82.8 \| 15.7 \| 26.1 \| 11.1 \| 14.9 \| 38.6 \| 45.3 \|`
Codeforces	coding	14.9	low	`\| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) \| ✅ \| 30.7 \| 22.0 \| 72.5 \| 82.8 \| 15.7 \| 26.1 \| 11.1 \| 14.9 \| 38.6 \| 45.3 \|`

none scraped.