arcflare_
Code32B official

olympiccoder

by Hugging Face (open-r1)

OlympicCoder 32B: a reasoning model trained for competitive programming, from Hugging Face's open-r1 project.

#code#reasoning#competitive
arcflare pull bartowski/open-r1_OlympicCoder-32B-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

olympiccoder

OlympicCoder 32B: a reasoning model trained for competitive programming, from Hugging Face's open-r1 project.

Get it

arcflare pull bartowski/open-r1_OlympicCoder-32B-GGUF:Q4_K_M
arcflare run open-r1_olympiccoder-32b

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

  • Thinks before answering: best on algorithmic problems, slower for edits
  • Open training recipe from the open-r1 project
  • Apache-2.0

Sizes

  • 32b · 19.9GB

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

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

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