← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · bf16 · 2026-05-25
Performance
16k
tokens
2,716
PP tok/s
51.8
TG tok/s
6034
TTFT (ms)
49.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,029 58.0 47.8 GB view
4k 2,657 55.9 48.5 GB view
8k 2,984 54.7 48.6 GB view
16k 2,716 51.8 49.1 GB current
32k 2,185 45.5 50.0 GB view
64k 1,649 32.3 52.0 GB view