← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 4bit · 2026-04-13
Performance
16k
tokens
1,044
PP tok/s
70.2
TG tok/s
15697
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,117 101.2 14.2 GB view
4k 1,358 95.0 14.7 GB view
8k 1,246 84.6 14.8 GB view
16k 1,044 70.2 15.2 GB current