← Back to community benchmarks

Ternary-Bonsai-27B

M5 Pro (20c) · 48 GB · 2bit · 2026-07-18
Performance
1k
tokens
477.5
PP tok/s
28.8
TG tok/s
2145
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.1
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 477.5 28.8 8.9 GB current
64k 186.0 17.9 13.9 GB view
Batching Results
Batch Size TG tok/s Speedup
28.8 1.00×
45.2 1.57×