Polaris-4B-Preview-GGUF

Home/Models/Mungert/Polaris-4B-Preview-GGUF

Mungert/Polaris-4B-Preview-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: —
root model: Qwen/Qwen3-4B
provider: Mungert
license: apache-2.0
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 81
likes: 0
created: —
last modified: 2025-09-24T15:43:28+00:00 (2025)
huggingface: https://huggingface.co/Mungert/Polaris-4B-Preview-GGUF
tags: ggufenbase_model:Qwen/Qwen3-4Bbase_model:quantized:Qwen/Qwen3-4Blicense:apache-2.0endpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
MATH	math	69.8	Skywork-OR1-7B-Math	medium	`\| Skywork-OR1-7B-Math \| 69.8 \| 52.3 \| 40.8 \| 63.2 \| 85.3 \|`
Math Olympiad	math	56.8		low	`\| Deepseek-R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 36.7 \| 56.8 \| 81.9 \|`
AIME 2024	math	55.0		low	`\| Deepseek-R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 36.7 \| 56.8 \| 81.9 \|`
AIME 2025	math	39.7		low	`\| Deepseek-R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 36.7 \| 56.8 \| 81.9 \|`
MATH	math	36.7		low	`\| Deepseek-R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 36.7 \| 56.8 \| 81.9 \|`

none scraped.