gpt-oss-20b
Run GPT-OSS 20B on a Mac
OpenAI's open-weight reasoner, native to the Harmony dual-channel format — rapid-mlx separates its analysis channel from the final answer automatically, with grammar-constrained tool calling on by default. Strong reasoning for its footprint.
MoE · 20 B total · MXFP4-Q8 · reasoningreasoning · OpenAI-style outputs · 16–32 GB Macs
OpenAI 128K context Base model intelligence 15.2 AA
One command
rapid-mlx serve gpt-oss-20b
Weights (10 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="gpt-oss-20b". 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 | 77.2 tok/s | 2.8 s | 15.7 GB | — | 10 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: 126.7 tok/s aggregate.
Community runs, one page per Mac: Apple M2 Pro · Apple M5 Max.
On the March 2026 M3 Ultra capability benchmark it scored 80% on tool calling. Full benchmark →
Will it fit your Mac?
Measured 15.7 GB Metal peak (6.0 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: In our end-to-end agent tests it reasons well but couldn't reliably drive Codex CLI's apply_patch edit format — for Codex, serve Qwen3.6 35B instead.
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
gpt-oss-20b-mxfp4-q4— The Q4 variant — smaller, slightly lossiergpt-oss-120b— GPT-OSS 120B — the big sibling for 96 GB+ Macs
FAQ
How much memory does GPT-OSS 20B need on a Mac?
Measured 15.7 GB Metal peak (6.0 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 GPT-OSS 20B on Apple Silicon?
We measured 77.2 tok/s on a Mac mini M4 Pro · 48 GB, rapid-mlx 0.15.4, 2026-10-02; peak memory 15.7 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 GPT-OSS 20B locally?
rapid-mlx serve gpt-oss-20b — 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.