● FitLLM — fit receipt · 8-bit · 8K tokens ctx · KV F16 · engine 2.16.0 · revision f1e3678550d69a40971615209e14e399144b2272 · release manifest

gpt-oss-120b on Mac 32GB

WON'T FIT ✗

weights	KV cache	overhead	reserve	total	short by
109 GB	0.3 GB	13.3 GB	8.5 GB	131 / 32 GB	98.9 GB

→ A 192GB+ Mac would fit.

Replay: npx fitllm-engine "gpt-oss-120b" --mac 32 · JSON · interactive

— embed: ![fits](https://img.shields.io/endpoint?url=https%3A%2F%2Ffitllm.run%2Fapi%2Fbadge%3Fmodel%3Dgpt-oss-120b%26ram%3D32%26quant%3D8%26ctx%3D8192%26kv%3D16)

Computed by the open fitllm-engine (MIT) from official config.json values — estimates; runtime varies. Ran it for real? Challenge this prediction — measured reports calibrate the engine for everyone.