qwen3-8b-4bit
Run Qwen3 8B on a Mac
The previous-generation Qwen3 8B — still one of the most-pulled aliases because a lot of guides reference it. If you're choosing fresh, Qwen3.5 9B is the same footprint and newer.
8 B dense · 4-bitguide compatibility · 16 GB Macs
Alibaba 40K context Base model intelligence 8.3 AA
One command
rapid-mlx serve qwen3-8b-4bit
Weights (4.3 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.
Measured on real hardware
Headline machine · Mac mini M2 Pro · 32 GB
All measured machines
| Machine | Decode | First token | Peak memory | Cold boot | Weights |
|---|---|---|---|---|---|
| Mac mini M2 Pro · 32 GB | 37.1 tok/s | 0.62 s | 5.1 GB | 4.7 s | 4.3 GB |
Measured on rapid-mlx 0.12.10, 2026-08-11. Decode: median of 3 runs, temperature 0, 256-token saturating generation, engine-reported token counts, unique salt per request (no prefix-cache hits). TTFT: median of 3, short prompt. Boot: process spawn to first completed token. Peak RSS: 0.5 s sampling across the run.
Will it fit your Mac?
Peak resident memory measured 5.1 GB during a 256-token generation. The KV cache grows with context length, so treat that as a floor, not a ceiling. 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 & alternatives
qwen3.5-9b-4bit— Qwen3.5 9B — the current generation at the same size
FAQ
How much memory does Qwen3 8B need on a Mac?
Measured peak resident memory was 5.1 GB on rapid-mlx 0.12.10 during a 256-token generation (M2 Pro, 32 GB). The weights are 4.3 GB on disk. Longer contexts grow the KV cache beyond this, so leave headroom.
How fast is Qwen3 8B on Apple Silicon?
We measured 37.1 tokens/sec sustained decode and 0.62 s time-to-first-token on a Mac mini M2 Pro (32 GB), median of 3 runs at temperature 0.
How do I run Qwen3 8B locally?
Install rapid-mlx (curl -fsSL https://rapidmlx.com/install.sh | bash, or brew install rapid-mlx), then: rapid-mlx serve qwen3-8b-4bit — the weights download on first run and you get an OpenAI-compatible endpoint at localhost:8000/v1 that works with Cursor, Claude Code, Aider, and any OpenAI client.