← Back to community benchmarks

Phi-4-mini-reasoning

M4 (10c) · 16 GB · 4bit · 2026-04-27
Performance
16k
tokens
339.8
PP tok/s
21.1
TG tok/s
48213
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 433.3 39.8 2.7 GB view
4k 437.7 33.5 3.4 GB view
8k 401.1 27.5 3.6 GB view
16k 339.8 21.1 4.5 GB current
Batching Results
Batch Size TG tok/s Speedup
39.8 1.00×
73.1 1.84×
95.0 2.39×