arcflare_
Code22B official

codestral

by Mistral AI

Codestral 22B: Mistral's dedicated code model, trained on 80+ languages. Non-production licence: research and personal use only.

#code#fim#non-commercial
arcflare pull bartowski/Codestral-22B-v0.1-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

codestral

Codestral 22B: Mistral's dedicated code model, trained on 80+ languages. Non-production licence: research and personal use only.

Get it

arcflare pull bartowski/Codestral-22B-v0.1-GGUF:Q4_K_M
arcflare run codestral-22b-v0.1

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

  • Instruct and fill-in-the-middle in one model
  • Not for production or commercial use: the MNPL is a non-production licence
  • For a commercial-friendly Mistral coder, see devstral2-small

Sizes

  • 22b · 13.3GB

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

[ 03 ] // relatedmore →

mellum

JetBrains

Code

Mellum 4B: JetBrains' completion model. A base model built for fill-in-the-middle autocomplete, not chat.

size
4B
vram
~5 GB
license
Apache-2.0

21% of a 24 GB card

#code #autocomplete #fim

seed-coder

ByteDance Seed

Code

Seed-Coder 8B: a strong small coding model, with a separate reasoning variant. MIT licensed.

size
8B
vram
~7 GB
license
MIT

29% of a 24 GB card

#code #small #reasoning

deepseek-coder-v2-lite

DeepSeek

Code

DeepSeek-Coder-V2-Lite: a 16B mixture-of-experts coder with a long context. Cheap to run for its size.

size
16B
vram
~12 GB
license
DeepSeek License

50% of a 24 GB card

#code #moe #long-context