← Back to community benchmarks

HY-MT1.5-7B

M5 Pro (20c) · 64 GB · 4bit · 2026-07-04
Performance
1k
tokens
1,352
PP tok/s
56.4
TG tok/s
757
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,352 56.4 4.7 GB current
4k 1,541 51.2 5.3 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 56.4 1.00×
2× 93.9 1.66×
4× 131.9 2.34×
8× 134.1 2.38×