← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-13
Performance
8k
tokens
1,423
PP tok/s
87.4
TG tok/s
5757
TTFT (ms)
30.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 1,423 87.4 30.9 GB current
16k 1,373 62.4 31.3 GB view
32k 1,243 39.8 32.0 GB view
64k 1,029 10.1 33.8 GB view