← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (32c) · 36 GB · 4bit · 2026-05-02
Performance
16k
tokens
1,072
PP tok/s
71.7
TG tok/s
15289
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 904.7 89.7 14.3 GB view
4k 1,112 85.4 14.9 GB view
8k 1,154 80.5 15.1 GB view
16k 1,072 71.7 15.6 GB current
32k 957.9 60.1 16.5 GB view
64k 813.8 48.2 18.5 GB view