gpt-4o-mini on M3 Pro (18-core GPU) + 36GB unified
M3 Pro (18-core GPU) + 36GB unified
suite suite-v1
cli 0.0.1-dev
signedS8711zXnps…
submitted Apr 26, 2026Workload results
| Workload | Backend | Model | decode tok/s | prefill tok/s | TTFT | p50 | p95 |
|---|---|---|---|---|---|---|---|
| chat-short | hosted-api | openai/gpt-4o-mini | 158.4tok/s | 106.2tok/s | 998ms | 0.0ms | 18.5ms |
Related benchmarks
- More gpt-4o-mini benchmarks — every backend and rig that has run this model.
- More M3 Pro (18-core GPU) LLM benchmarks — every model measured on this hardware.
Provenance
- Run ID
- r_mya-83a8n3j
- Fingerprint hash
- a52e5dd258afe436
- Public key
- S8711zXnpsbOS9F8EZCne0DE3jWiyeYAqEDECBzTVWk=
- Received
- 2026-04-26 16:30:53