Chat30B-A3B official

qwen3-30b-a3b-instruct-2507

by Alibaba Qwen

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

#chat #instruct #moe #large

arcflare pull unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

qwen3-30b-a3b-instruct-2507

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

Get it

arcflare pull unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

arcflare run qwen3-30b-a3b-instruct-2507

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: 18.6 GB. Also published: Q8_0 (32.5 GB), Q5_K_M (21.7 GB), Q3_K_M (14.7 GB)
Trained for a 256K context
Licence: Apache-2.0. Read it before commercial use

Sizes

30b-a3b · 18.6GB

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

[ 03 ] // relatedmore →

llama3.3-70b

qwen3-32b

Alibaba Qwen

Chat

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

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

88% of a 24 GB card

#chat #instruct #large

granite-4-0-h-tiny

IBM

Chat

IBM 7B-parameter (1B active) hybrid long-context instruct model with improved instruction following and tool calling.

size: 7B-A1B
vram: ~6 GB
license: Apache-2.0

25% of a 24 GB card

#chat #instruct #moe