qwen3.5-9b-4bit
Run Qwen3.5 9B on a Mac
The sweet spot of the Qwen3.5 dense line for 16 GB Macs: measurably smarter than the 4B on tool calling and code, a 6 GB download that fits alongside the OS and a browser.
9 B dense · 4-bit16 GB Macs · tool calling · general assistant work
Alibaba 256K context Base model intelligence 21.8 AA
One command
rapid-mlx serve qwen3.5-9b-4bit
Weights (5.98 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="qwen3.5-9b-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 0.15.4 · 2026-10-02 raw data | 63.0 tok/s | 5.3 s | 8.0 GB | — | 5.98 GB |
Each row cites its own run; numbers are never copied across machines. Mac mini M4 Pro · 48 GB: rapid-mlx 0.15.4, 2026-10-02 — raw data + method — 4 concurrent streams: 62.4 tok/s aggregate.
Community runs, one page per Mac: Apple M2 Pro · Apple M4 Pro · Apple M5 Max.
On the March 2026 M3 Ultra capability benchmark it scored 83% on tool calling and 70% on code. Full benchmark →
Will it fit your Mac?
Measured 8.0 GB Metal peak (5.6 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
qwen3.5-4b-4bit— Qwen3.5 4B — smaller and fasterqwen3.6-35b— Qwen3.6 35B MoE — the flagship, if you have the memory
FAQ
How much memory does Qwen3.5 9B need on a Mac?
Measured 8.0 GB Metal peak (5.6 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 Qwen3.5 9B on Apple Silicon?
We measured 63.0 tok/s on a Mac mini M4 Pro · 48 GB, rapid-mlx 0.15.4, 2026-10-02; peak memory 8.0 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 Qwen3.5 9B locally?
rapid-mlx serve qwen3.5-9b-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.