HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Home/Models/unsloth/Magistral-Small-2506-GGUF

Magistral-Small-2506-GGUF

unsloth/Magistral-Small-2506-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: —
root model: mistralai/Magistral-Small-2506
provider: unsloth
license: apache-2.0
language: en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa
context: 40,960
library: —
vRAM (GB): —
size on disk: —
downloads: 1,264
likes: 96
created: —
last modified: 2025-07-24T22:47:22+00:00 (2025)
huggingface: https://huggingface.co/unsloth/Magistral-Small-2506-GGUF
tags: ggufmistralunslothenfrdeesptitjakoruzharfaidmsneplrosrsvtruk

Benchmark scores (4)

benchmark	category	score	context	conf	evidence
AIME 2024	math	73.59		low	`\| Magistral Medium \| 73.59% \| 64.95% \| 70.83% \| 59.36% \|`
GPQA Diamond	reasoning	70.83		low	`\| Magistral Medium \| 73.59% \| 64.95% \| 70.83% \| 59.36% \|`
AIME 2025	math	64.95		low	`\| Magistral Medium \| 73.59% \| 64.95% \| 70.83% \| 59.36% \|`
LiveCodeBench	coding	59.36		low	`\| Magistral Medium \| 73.59% \| 64.95% \| 70.83% \| 59.36% \|`

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.