← Back to community benchmarks

gemma-4-26b-a4b

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-08
Performance
16k
tokens
1,637
PP tok/s
71.1
TG tok/s
10007
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
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
4k 450.2 81.3 26.2 GB view
8k 1,683 76.4 26.6 GB view
16k 1,637 71.1 26.7 GB current
32k 1,492 59.9 27.5 GB view
64k 1,229 45.8 29.2 GB view
128k 878.7 30.6 32.7 GB view