Reasoning36B official

seed-oss-36b-instruct

by ByteDance Seed

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

#reasoning #large

arcflare pull unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

seed-oss-36b-instruct

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

Get it

arcflare pull unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_M

arcflare run seed-oss-36b-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: 21.8 GB. Also published: Q3_K_M (17.6 GB), Q5_K_M (25.6 GB), Q8_0 (38.4 GB)
Trained for a 512K context
Licence: Apache-2.0. Read it before commercial use

Sizes

36b · 21.8GB

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

deepseek-r1-distill-qwen-32b

DeepSeek

Reasoning

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

size: 32B
vram: ~21 GB
license: MIT

88% of a 24 GB card

#reasoning #large