← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Ultra (76c) · 192 GB · 4bit · 2026-05-05
Performance
16k
tokens
1,197
PP tok/s
67.5
TG tok/s
13685
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.3.8
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 988.3 86.6 13.6 GB view
4k 1,175 82.1 14.2 GB view
8k 1,217 77.0 14.4 GB view
16k 1,197 67.5 14.8 GB current
32k 1,124 54.9 15.8 GB view
64k 944.5 39.1 17.0 GB view
128k 645.0 24.6 20.5 GB view
Batching Results
Batch Size TG tok/s Speedup
86.6 1.00×
127.2 1.47×
173.1 2.00×
216.2 2.50×