Reasoning24B official

magistral-small-2509

by Mistral AI

24B reasoning model built on Mistral Small 3.2 with SFT from Magistral Medium traces and RL; 128K context window.

#reasoning

arcflare pull mistralai/Magistral-Small-2509-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

magistral-small-2509

24B reasoning model built on Mistral Small 3.2 with SFT from Magistral Medium traces and RL; 128K context window.

Get it

arcflare pull mistralai/Magistral-Small-2509-GGUF:Q4_K_M

arcflare run magistral-small-2509

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

Downloads the Q4_K_M file by default: 14.3 GB. Also published: Q8_0 (25.1 GB), Q5_K_M (16.8 GB)
Trained for a 128K context
Licence: Apache-2.0. Read it before commercial use

Sizes

24b · 14.3GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

gpt-oss

OpenAI

Reasoning

gpt-oss: OpenAI's open-weight reasoning models. 20B runs in ~16 GB, 120B on one 80 GB card. Apache-2.0, adjustable reasoning effort.

size: 20B
vram: ~14 GB
license: Apache-2.0

58% of a 24 GB card

#reasoning #tools #moe

glm4.5-air

Z.ai

Reasoning

GLM-4.5-Air: a 106B MoE with 12B active, hybrid reasoning and strong agent and coding scores, under MIT. Workstation-class.

size: 106B-A12B
vram: ~64 GB
license: MIT

2.7× a 24 GB card

#moe #agentic #reasoning

deepseek-r1-0528

DeepSeek

Reasoning

DeepSeek-R1-0528: the updated 671B reasoning model, plus an 8B distill on Qwen3 that runs on a gaming GPU. MIT.

size: 8B
vram: ~6 GB
license: MIT

25% of a 24 GB card

#reasoning #math #moe