HF Model & Benchmark Matrix

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

Devstral-Small-2-24B-Instruct-2512

mistralai/Devstral-Small-2-24B-Instruct-2512

kind
fp8
quant
fp8 (8-bit)
family
mistral
modality
—
root model
mistralai/Mistral-Small-3.1-24B-Base-2503
provider
mistralai
license
apache-2.0
language
—
context
—
library
vllm
vRAM (GB)
—
size on disk
—
downloads
251,726
likes
636
created
—
last modified
2026-07-15T12:20:36+00:00 (2026)
huggingface
https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512
tags
vllmsafetensorsmistral3mistral-commonarxiv:2501.19399base_model:mistralai/Mistral-Small-3.1-24B-Base-2503base_model:quantized:mistralai/Mistral-Small-3.1-24B-Base-2503license:apache-2.0fp8deploy:azureregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
SWE-bench Verifiedswe72.2low| **Devstral 2** | 123 | 72.2% | 61.3% | 32.6% |
Terminal-Benchagentic-coding32.6low| **Devstral 2** | 123 | 72.2% | 61.3% | 32.6% |

Discussions (0)

none scraped.

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