← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 256 GB · unknown · 2026-06-04
Performance
16k
tokens
1,553
PP tok/s
55.6
TG tok/s
10552
TTFT (ms)
48.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.4.0
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,553 55.6 48.7 GB current
32k 1,398 49.0 50.0 GB view
64k 1,163 38.6 52.0 GB view