← Back to community benchmarks

gemma-4-26B-A4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-07
Performance
16k
tokens
3,295
PP tok/s
74.8
TG tok/s
4972
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 3,238 80.8 26.3 GB view
16k 3,295 74.8 27.1 GB current
32k 3,057 65.8 28.0 GB view
64k 2,410 52.2 30.0 GB view