arcflare_
Code32B official

qwen2.5-coder-32b

by Alibaba Qwen

Code-specific instruction-tuned 32B Qwen2.5-Coder model, improved at code generation, code reasoning and code fixing.

#code#instruct#large
arcflare pull Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:q4_k_m

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

qwen2.5-coder-32b

Code-specific instruction-tuned 32B Qwen2.5-Coder model, improved at code generation, code reasoning and code fixing.

Get it

arcflare pull Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:q4_k_m
arcflare run qwen2.5-coder-32b-instruct

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

  • Downloads the q4_k_m file by default: 19.9 GB. Also published: q8_0 (34.8 GB), q6_k (26.9 GB), q5_k_m (23.3 GB)
  • Trained for a 32K context
  • Licence: Apache-2.0. Read it before commercial use

Sizes

  • 32b · 19.9GB

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

[ 03 ] // relatedmore →

qwen2.5-coder

Alibaba Qwen

Code

Code-specific instruction-tuned 7B Qwen2.5-Coder model, improved at code generation, code reasoning and code fixing.

size
7B
vram
~6 GB
license
Apache-2.0

25% of a 24 GB card

#code #instruct

starcoder2

BigCode

Code

Code LLM self-aligned from StarCoder2-15B with a fully permissive, transparent pipeline and no human annotations or distilled data.

size
15B
vram
~11 GB
license
BigCode OpenRAIL-M

46% of a 24 GB card

#code #instruct

qwen2.5-coder-14b-instruct

Qwen

Code

Instruction-tuned 14B code model with improved code generation, reasoning and fixing, and long-context support up to 128K tokens.

size
14B
vram
~10 GB
license
Apache-2.0

42% of a 24 GB card

#code #instruct