arcflare_
Code4B official

mellum

by JetBrains

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

#code#autocomplete#fim#small
arcflare pull JetBrains/Mellum-4b-base-gguf:Q8_0

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

mellum

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

Get it

arcflare pull JetBrains/Mellum-4b-base-gguf:Q8_0
arcflare run mellum-4b-base

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

  • A base model: point an editor's FIM autocomplete at arcflare serve, don't chat with it
  • Published as Q8_0 GGUF by JetBrains
  • Apache-2.0

Sizes

  • 4b · 4.3GB

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

[ 03 ] // relatedmore →

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

codestral

Mistral AI

Code

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

size
22B
vram
~15 GB
license
Mistral Non-Production

63% of a 24 GB card

#code #fim #non-commercial

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