arcflare_
Chat4B official

gemma3-4b

by Google

Google's multimodal Gemma 3 4B instruction-tuned model: text and image input, text output, 128K context, 140+ languages.

#chat#instruct#vision#small
arcflare pull unsloth/gemma-3-4b-it-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

gemma3-4b

Google's multimodal Gemma 3 4B instruction-tuned model: text and image input, text output, 128K context, 140+ languages.

Get it

arcflare pull unsloth/gemma-3-4b-it-GGUF:Q4_K_M
arcflare run gemma-3-4b-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

  • Downloads the Q4_K_M file by default: 2.5 GB. Also published: Q8_0 (4.1 GB), Q6_K (3.2 GB), Q5_K_M (2.8 GB)
  • Reads images: the download also fetches the vision projector (mmproj), about 1 GB more
  • Trained for a 128K context
  • Licence: Gemma. Read it before commercial use

Sizes

  • 4b · 2.5GB

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

[ 03 ] // relatedmore →

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

llama3.2-1b

Meta

Chat

Meta's 1B multilingual instruction-tuned text model, optimized for dialogue, agentic retrieval and summarization tasks.

size
1B
vram
~2 GB
license
Llama 3.2 Community

8% of a 24 GB card

#chat #instruct #small

mistral-small-3.2-24b

Mistral AI

Chat

Mistral Small 3.1 update with better instruction following, fewer repetitive outputs and more robust function calling; text and image input.

size
24B
vram
~17 GB
license
Apache-2.0

71% of a 24 GB card

#chat #instruct #vision