arcflare_
Chat8B official

qwen3

by Alibaba Qwen

Qwen3 runs from 0.6B to 235B, dense and MoE, with thinking and non-thinking modes in one model. Apache-2.0 across the board.

#chat#reasoning#tools#moe#multilingual
arcflare pull unsloth/Qwen3-8B-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

qwen3

Qwen3 runs from 0.6B to 235B, dense and MoE, with thinking and non-thinking modes in one model. Apache-2.0 across the board.

Get it

arcflare pull unsloth/Qwen3-8B-GGUF:Q4_K_M
arcflare run qwen3-8b

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

  • Switch thinking on and off per message with /think and /no_think
  • 30B-A3B MoE: 30B of knowledge at about 3B of compute per token, fast even on modest GPUs
  • 119 languages and strong tool calling
  • Native 32K context, extendable to 128K with YaRN

Sizes

  • 0.6b · 0.5GB
  • 1.7b · 1.3GB
  • 4b · 2.5GB
  • 8b · 5.0GB
  • 14b · 9.0GB
  • 32b · 20GB
  • 30b-a3b · 18GB
  • 235b-a22b · 142GB

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

[ 03 ] // relatedmore →

qwen3.5

Alibaba Qwen

Chat

Qwen3.5: Qwen's 2026 generation, 2B to 35B-A3B, with a 256K native context and strong coding for a general model.

size
27B
vram
~18 GB
license
Apache-2.0

75% of a 24 GB card

#chat #code #reasoning

smollm3

Hugging Face

Chat

SmolLM3 3B: a fully open small model with switchable reasoning, multilingual output and long context. Its training recipe is published too.

size
3B
vram
~2.5 GB
license
Apache-2.0

10% of a 24 GB card

#small #reasoning #multilingual

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