llama3-3b-4bit
Run Llama 3.2 3B on a Mac
Meta's Llama 3.2 3B Instruct — a safe, widely-fine-tuned baseline that many downstream tools assume. 121 tok/s on a 48 GB M4 Pro from a 1.5 GB download.
3 B dense · 4-bitLlama-ecosystem compatibility · everyday chat
Meta 128K context Base model intelligence 3.9 AA
One command
rapid-mlx serve llama3-3b-4bit
Weights (1.5 GB) download on first run; you get an OpenAI-compatible
endpoint at http://localhost:8000/v1. No rapid-mlx yet? It's one line —
curl -fsSL https://rapidmlx.com/install.sh | bash — or take the
desktop app.
Point a client at it. OpenAI SDK: base_url="http://localhost:8000/v1",
model="llama3-3b-4bit". Claude Code:
ANTHROPIC_BASE_URL=http://localhost:8000 (no /v1 suffix) —
see the Claude Code guide.
Measured on real hardware
Headline machine · Mac mini M4 Pro · 48 GB
All measured machines
| Machine | Decode | First token | Peak memory | Cold boot | Weights |
|---|---|---|---|---|---|
| Mac mini M4 Pro · 48 GB rapid-mlx 0.15.5 · 2026-10-03 raw data | 121.2 tok/s | 2.2 s | 14.4 GB | — | 1.5 GB |
Each row cites its own run; numbers are never copied across machines. Mac mini M4 Pro · 48 GB: rapid-mlx 0.15.5, 2026-10-03 — raw data + method — 4 concurrent streams: 255.4 tok/s aggregate.
Will it fit your Mac?
Measured 14.4 GB Metal peak (2.1 GB process RSS) on a 48 GB M4 Pro across the whole benchmark run — up to a ~16K-token prompt and four concurrent streams, including the engine's prefix cache, which defaults to 20% of RAM. A short chat needs less; long contexts grow the KV cache, so leave headroom.
For the conservative install-default placement see the hardware tiers table; to compare against every model your RAM can hold, use the live picker.
Variants & profiles
qwen3-4b-instruct-2507-4bit— Qwen3 4B Instruct — stronger at a similar size
FAQ
How much memory does Llama 3.2 3B need on a Mac?
Measured 14.4 GB Metal peak (2.1 GB process RSS) on a 48 GB M4 Pro across the whole benchmark run — up to a ~16K-token prompt and four concurrent streams, including the engine's prefix cache, which defaults to 20% of RAM. A short chat needs less; long contexts grow the KV cache, so leave headroom.
How fast is Llama 3.2 3B on Apple Silicon?
We measured 121.2 tok/s on a Mac mini M4 Pro · 48 GB, rapid-mlx 0.15.5, 2026-10-03; peak memory 14.4 GB on that run. Every row on this page keeps its own chip, version and date — no number is copied across machines.
How do I run Llama 3.2 3B locally?
rapid-mlx serve llama3-3b-4bit — the weights download on first run and you get an OpenAI-compatible endpoint at localhost:8000/v1 for Aider, Codex and any OpenAI client, plus the Anthropic API at localhost:8000 for Claude Code.