arcflare_
Code72B official

kimi-dev

by Moonshot AI

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

#code#swe#agentic
arcflare pull unsloth/Kimi-Dev-72B-GGUF:IQ4_XS

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

kimi-dev

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

Get it

arcflare pull unsloth/Kimi-Dev-72B-GGUF:IQ4_XS
arcflare run kimi-dev-72b

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 for issue-resolution workflows
  • This repo has no Q4_K_M; IQ4_XS is the closest quant at a similar size
  • MIT licensed

Sizes

  • 72b · ~39GB

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

[ 03 ] // relatedmore →

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

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

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