← Back to community benchmarks

HY-MT1.5-7B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
16k
tokens
1,595
PP tok/s
58.4
TG tok/s
10272
TTFT (ms)
7.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,566 92.3 4.9 GB view
4k 1,524 86.7 5.5 GB view
8k 1,589 77.5 6.3 GB view
16k 1,595 58.4 7.7 GB current
32k 1,407 38.6 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
92.3 1.00×
121.6 1.32×
129.2 1.40×