Llama-3.2-3B-F1-Reasoning-Instruct-GGUF

Home/Models/Mungert/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF

Mungert/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: llama
modality: —
root model: meta-llama/Llama-3.2-3B
provider: Mungert
license: llama3.2
language: en, zh
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 122
likes: 4
created: —
last modified: 2025-09-24T15:42:22+00:00 (2025)
huggingface: https://huggingface.co/Mungert/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF
tags: transformersggufTaiwanR.O.CzhtwSLMLlama-32enzhdataset:lianghsun/tw-reasoning-instructdataset:minyichen/tw-instruct-R1-200kdataset:minyichen/tw_mm_R1base_model:lianghsun/Llama-3.2-3B-F1-Basebase_model:quantized:lianghsun/Llama-3.2-3B-F1-Baselicense:llama3.2model-indexendpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
MATH-500	math	44.4		low	`\| [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) \| 44.40 \| 27.78 \|`
GPQA Diamond	reasoning	27.78		low	`\| [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) \| 44.40 \| 27.78 \|`

none scraped.