arcflare_
Chat270M official

gemma3-270m

by Google

Gemma 3 270M: a tiny model built to be fine-tuned for one narrow job. Runs on anything, including a CPU.

#tiny#fine-tuning#cpu#edge
arcflare pull unsloth/gemma-3-270m-it-GGUF:Q8_0

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

gemma3-270m

Gemma 3 270M: a tiny model built to be fine-tuned for one narrow job. Runs on anything, including a CPU.

Get it

arcflare pull unsloth/gemma-3-270m-it-GGUF:Q8_0
arcflare run gemma-3-270m-it

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

  • Small enough to run beside a big model as a router or classifier
  • Strong instruction following for its size
  • Made to be specialised: fine-tune it for one task and it beats generalists many times its size

Sizes

  • 270m · 0.3GB

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

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