qwen3.6-35b
Run Qwen3.6 35B (A3B MoE) on a Mac
Run it
Install: pip install rapid-mlx or Rapid-MLX Desktop.
rapid-mlx serve qwen3.6-35b
Minimum RAM: No published minimum; 23.2 GB measured peak. Leave macOS and context headroom. Agent setup guide
The flagship local agent model: 35 B of capability decoding at 104.5 tok/s on a 48 GB M4 Pro because only ~3 B parameters are active per token. This is the model our release gate drives real coding agents with.
MoE · 35 B total / 3 B active · 4-bitcoding agents · the 32 GB Mac flagship · Tier-1 family
Alibaba 256K context Base model intelligence 32.1 AA
First request
rapid-mlx serve qwen3.6-35b
Weights (17.5 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="qwen3.6-35b". 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 | 104.5 tok/s | 2.4 s | 23.2 GB | — | 17.5 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: 106.5 tok/s aggregate.
Community runs, one page per Mac: Apple M3 Ultra · Apple M4 Pro · Apple M5 Pro.
Will it fit your Mac?
Measured 23.2 GB Metal peak (18.7 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.
Agents: This exact 4-bit build drove Codex CLI's apply_patch edit format first-try in our end-to-end tests, and the 8-bit build is what our Tier-1 agent release gate runs Claude Code, Codex, Hermes and Aider against on every release.
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
qwen3.6-35b-mxfp4— The MXFP4 variantqwen3-coder-30b-4bit— Qwen3 Coder 30B — the code specialist
FAQ
How much memory does Qwen3.6 35B (A3B MoE) need on a Mac?
Measured 23.2 GB Metal peak (18.7 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 Qwen3.6 35B (A3B MoE) on Apple Silicon?
We measured 104.5 tok/s on a Mac mini M4 Pro · 48 GB, rapid-mlx 0.15.4, 2026-10-02; peak memory 23.2 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 Qwen3.6 35B (A3B MoE) locally?
rapid-mlx serve qwen3.6-35b — 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.