Chat1B official

llama3.2-1b

by Meta

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

#chat #instruct #small

arcflare pull unsloth/Llama-3.2-1B-Instruct-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

llama3.2-1b

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

Get it

arcflare pull unsloth/Llama-3.2-1B-Instruct-GGUF:Q4_K_M

arcflare run llama-3.2-1b-instruct

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: 0.8 GB. Also published: Q8_0 (1.3 GB), Q6_K (1 GB), Q5_K_M (0.9 GB)
Trained for a 128K context
Licence: Llama 3.2 Community. Read it before commercial use

Sizes

1b · 0.8GB

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

[ 03 ] // relatedmore →

llama3.2

gemma3-4b

Google

Chat

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

size: 4B
vram: ~5 GB
license: Gemma

21% of a 24 GB card

#chat #instruct #vision

gemma3n-e4b

Google

Chat

Google's Gemma 3n E4B instruction-tuned model for low-resource devices, effective 4B parameters, 32K context; this GGUF is text-only.

size: E4B
vram: ~6 GB
license: Gemma

25% of a 24 GB card

#chat #instruct #small