← Back to community benchmarks

HY-MT1.5-7B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-14
Performance
8k
tokens
1,352
PP tok/s
58.4
TG tok/s
6059
TTFT (ms)
9.0
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,309 70.3 8.2 GB view
4k 1,420 64.5 8.5 GB view
8k 1,352 58.4 9.0 GB current
16k 1,205 49.1 10.0 GB view
32k 980.4 37.0 12.1 GB view
64k 712.4 5.3 71.8 GB view
Batching Results
Batch Size TG tok/s Speedup
70.3 1.00×
115.3 1.64×
183.7 2.61×
225.5 3.21×