arcflare_
Code24B official

devstral

by Mistral AI & All Hands

Devstral Small 24B: built for agentic coding. It navigates a repo, edits files and runs tests, the way the ArcFlare agent and OpenCode work.

#code#agentic#tools#swe
arcflare pull unsloth/Devstral-Small-2505-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

devstral

Devstral Small 24B: built for agentic coding. It navigates a repo, edits files and runs tests, the way the ArcFlare agent and OpenCode work.

Get it

arcflare pull unsloth/Devstral-Small-2505-GGUF:Q4_K_M
arcflare run devstral-small-2505

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

  • Trained on real software-engineering tasks, not just completion
  • Pairs well with arcflare agent and arcflare use opencode
  • Apache-2.0

Sizes

  • 24b · 14GB

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

[ 03 ] // relatedmore →

devstral2-small

Mistral AI

Code

Devstral Small 2 (24B, 2512): Mistral's second-generation agentic coder, with a 256K context, under Apache-2.0.

size
24B
vram
~16 GB
license
Apache-2.0

67% of a 24 GB card

#code #agentic #tools

kimi-dev

Moonshot AI

Code

Kimi-Dev 72B: Moonshot's open model for fixing real GitHub issues: it finds the bug, writes the patch, and checks it.

size
72B
vram
~42 GB
license
MIT

1.8× a 24 GB card

#code #swe #agentic

glm4.7-flash

Z.ai

Code

GLM-4.7-Flash: a 30B-A3B MoE built for agentic coding. Only ~3B parameters active per token, so it runs at small-model speed.

size
30B-A3B
vram
~20 GB
license
MIT

83% of a 24 GB card

#code #agentic #moe