OpenMath-Nemotron-32B-GGUF

Home/Models/Mungert/OpenMath-Nemotron-32B-GGUF

Mungert/OpenMath-Nemotron-32B-GGUF

kind: gguf
quant: gguf (16-bit)
family: nemotron
modality: —
root model: Qwen/Qwen2.5-32B
provider: Mungert
license: cc-by-4.0
language: en
context: 131,072
library: transformers
vRAM (GB): —
size on disk: —
downloads: 60
likes: 1
created: —
last modified: 2025-09-24T15:42:12+00:00 (2025)
huggingface: https://huggingface.co/Mungert/OpenMath-Nemotron-32B-GGUF
tags: transformersggufnvidiamathendataset:nvidia/OpenMathReasoningarxiv:2504.16891base_model:Qwen/Qwen2.5-32Bbase_model:quantized:Qwen/Qwen2.5-32Blicense:cc-by-4.0endpoints_compatibleregion:usconversational

benchmark	category	score	conf	evidence
AIME 2024	math	83.3	low	`\| + Self GenSelect \| 83.3 \| 70.0 \| 62.2 \| 7.9 \|`
AIME 2025	math	70.0	low	`\| + Self GenSelect \| 83.3 \| 70.0 \| 62.2 \| 7.9 \|`
Humanity's Last Exam	knowledge	7.9	low	`\| + Self GenSelect \| 83.3 \| 70.0 \| 62.2 \| 7.9 \|`

none scraped.