~/model/meta-llama/Llama-3.2-1B-Instruct

Llama 3.2 1B

Sub-2B edge tier. Runs on phones and 8GB consumer cards. Multilingual instruct.

Parameters

1.23B

Family

Meta

Context

128K tokens

FP16 weights

2.5GB

// where you can run it

llama3.2:1b LM Studio vLLM MLX oMLX

// hugging face stats (cached daily)

7.9M downloads · 1K likes · license: llama3.2 · updated 1 year ago

What you need to run this.

$ ./vrambudget --model llama-3-2-1b --by quant

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json

$ similarLlama 3.2 3B3.21BMeta $ similarPhi-4 Mini3.8BMicrosoft $ similarGemma 4 E4B4BGoogle $ similarQwen 2.5 7B7BAlibaba

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.