Code24B official

devstral2-small

by Mistral AI

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

#code #agentic #tools #long-context

arcflare pull unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

devstral2-small

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

Get it

arcflare pull unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M

arcflare run devstral-small-2-24b-instruct-2512

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

The successor to devstral: same size, a much longer context
Made for agent harnesses: arcflare agent, OpenCode, Hermes
Apache-2.0

Sizes

24b · 14.3GB

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

[ 03 ] // relatedmore →

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

qwen3-coder-next

Alibaba Qwen

Code

Qwen3-Coder-Next: an 80B MoE with only 3B active, a 256K context, and training aimed at agent harnesses like Claude Code and Cline.

size: 80B-A3B
vram: ~52 GB
license: Apache-2.0

2.2× a 24 GB card

#code #agentic #moe

devstral

Mistral AI & All Hands

Code

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

size: 24B
vram: ~16 GB
license: Apache-2.0

67% of a 24 GB card

#code #agentic #tools