← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-18
Performance
8k
tokens
1,711
PP tok/s
76.8
TG tok/s
4788
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 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 1,326 84.1 25.8 GB view
4k 1,542 80.8 26.4 GB view
8k 1,711 76.8 26.6 GB current
16k 1,656 69.8 27.1 GB view
32k 1,500 59.1 28.0 GB view
64k 1,224 45.1 30.0 GB view
128k 879.4 27.7 32.7 GB view
Batching Results
Batch Size TG tok/s Speedup
84.1 1.00×
120.9 1.44×
170.9 2.03×