← Back to community benchmarks

HY-MT1.5-1.8B

M3 Max (40c) · 128 GB · 8bit · 2026-03-10
Performance
1k
tokens
2,220
PP tok/s
134.3
TG tok/s
461
TTFT (ms)
2.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,220 134.3 2.4 GB current
4k 2,461 115.4 2.7 GB view
Batching Results
Batch Size TG tok/s Speedup
134.3 1.00×
256.5 1.91×
376.3 2.80×