arcflare_
Chat27B official

qwen3.5

by Alibaba Qwen

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

#chat#code#reasoning#long-context
arcflare pull unsloth/Qwen3.5-27B-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

qwen3.5

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

Get it

arcflare pull unsloth/Qwen3.5-27B-GGUF:Q4_K_M
arcflare run qwen3.5-27b

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

  • 256K native context across the family
  • 35B-A3B MoE for speed, dense 27B for quality
  • Apache-2.0

Sizes

  • 2b · —
  • 4b · —
  • 9b · —
  • 27b · ~17GB
  • 35b-a3b · —

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

[ 03 ] // relatedmore →

qwen3

Alibaba Qwen

Chat

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.

size
8B
vram
~6 GB
license
Apache-2.0

25% of a 24 GB card

#chat #reasoning #tools

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

llama3.2

Meta

Chat

Meta's 3B multilingual instruction-tuned text model, optimized for dialogue, agentic retrieval and summarization tasks.

size
3B
vram
~3 GB
license
Llama 3.2 Community

13% of a 24 GB card

#chat #instruct #small