← Back to community benchmarks

Ternary-Bonsai-27B

M1 Max (32c) · 32 GB · 2bit · 2026-07-22
Performance
32k
tokens
134.0
PP tok/s
18.3
TG tok/s
244570
TTFT (ms)
13.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.5.2
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 155.6 25.2 8.9 GB view
4k 158.6 24.4 10.2 GB view
32k 134.0 18.3 13.3 GB current
64k 111.9 12.5 17.9 GB view
Batching Results
Batch Size TG tok/s Speedup
25.2 1.00×
27.2 1.08×
29.4 1.17×