← Back to community benchmarks

HY-MT1.5-1.8B

M4 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
1k
tokens
3,002
PP tok/s
261.5
TG tok/s
341
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,002 261.5 1.8 GB current
4k 3,335 212.1 1.9 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 261.5 1.00×
2× 445.0 1.70×
4× 539.5 2.06×
8× 1062.9 4.06×