arcflare_
Reasoning32B official

deepseek-r1-distill-qwen-32b

by DeepSeek

Qwen2.5-32B fine-tuned on DeepSeek-R1 reasoning data; card reports it outperforms OpenAI o1-mini across various benchmarks.

#reasoning#large
arcflare pull unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

deepseek-r1-distill-qwen-32b

Qwen2.5-32B fine-tuned on DeepSeek-R1 reasoning data; card reports it outperforms OpenAI o1-mini across various benchmarks.

Get it

arcflare pull unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
arcflare run deepseek-r1-distill-qwen-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

  • Downloads the Q4_K_M file by default: 19.9 GB. Also published: Q8_0 (34.8 GB), Q5_K_M (23.3 GB), Q3_K_M (15.9 GB)
  • Trained for a 128K context
  • Distilled from Qwen2.5, which is Apache-2.0
  • Licence: MIT. 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 →

qwen3-30b-a3b-thinking-2507

Alibaba Qwen

Reasoning

Qwen3-30B-A3B thinking-only update: 30.5B MoE with 3.3B active, deeper reasoning and 256K native context.

size
30B-A3B
vram
~20 GB
license
Apache-2.0

83% of a 24 GB card

#reasoning #moe #large

gpt-oss-120b

OpenAI

Reasoning

OpenAI open-weight MoE reasoning model, 117B parameters with 5.1B active, configurable reasoning effort, MXFP4-trained MoE weights.

size
117B-A5B
vram
~64 GB
license
Apache-2.0

2.7× a 24 GB card

#reasoning #moe #large

seed-oss-36b-instruct

ByteDance Seed

Reasoning

ByteDance Seed open-source LLM for long-context, reasoning and agent tasks, with flexible thinking-budget control and native 512K context.

size
36B
vram
~23 GB
license
Apache-2.0

96% of a 24 GB card

#reasoning #large