← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (60c) · 256 GB · bf16 · 2026-05-14
Performance
8k
tokens
1,614
PP tok/s
61.0
TG tok/s
5076
TTFT (ms)
48.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,238 65.1 47.8 GB view
4k 1,552 63.2 48.5 GB view
8k 1,614 61.0 48.6 GB current
16k 1,580 56.6 49.1 GB view
32k 1,444 49.6 49.5 GB view
64k 1,192 39.0 51.2 GB view
128k 849.2 26.9 54.8 GB view