← Back to community benchmarks

Ternary-Bonsai-8B

M4 Max (40c) · 48 GB · 2bit · 2026-04-17
Performance
16k
tokens
691.0
PP tok/s
69.0
TG tok/s
23711
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 897.7 128.1 2.9 GB view
4k 918.7 106.9 3.4 GB view
8k 830.8 87.9 3.9 GB view
16k 691.0 69.0 5.0 GB current
32k 531.4 48.5 7.3 GB view
64k 295.5 17.4 12.0 GB view