Chat32B official

qwen3-32b

by Alibaba Qwen

Qwen3 32.8B dense model switching between thinking and non-thinking modes; 32K context, 131K with YaRN, 100+ languages.

#chat #instruct #large

arcflare pull Qwen/Qwen3-32B-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

qwen3-32b

Qwen3 32.8B dense model switching between thinking and non-thinking modes; 32K context, 131K with YaRN, 100+ languages.

Get it

arcflare pull Qwen/Qwen3-32B-GGUF:Q4_K_M

arcflare run qwen3-32b

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: 19.8 GB. Also published: Q8_0 (34.8 GB), Q6_K (26.9 GB), Q5_K_M (23.2 GB)
Trained for a 32K context
Licence: Apache-2.0. Read it before commercial use

Sizes

32b · 19.8GB

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

[ 03 ] // relatedmore →

llama3.3-70b

qwen3-30b-a3b-instruct-2507

Alibaba Qwen

Chat

Qwen3-30B-A3B non-thinking update: 30.5B-parameter MoE with 3.3B active, 128 experts and 256K native context.

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

83% of a 24 GB card

#chat #instruct #moe

granite-4.0-h-small

IBM

Chat

32B-parameter long-context instruct model with improved instruction following and tool calling, finetuned from Granite-4.0-H-Small-Base.

size: 32B
vram: ~21 GB
license: Apache-2.0

88% of a 24 GB card

#chat #instruct #large