← Back to community benchmarks

gemma-4-26B-A4B-it-oQ5

M4 Max (40c) · 64 GB · 5bit · 2026-05-22
Performance
128k
tokens
695.9
PP tok/s
39.1
TG tok/s
188355
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,161 91.6 17.4 GB view
4k 1,379 89.8 17.7 GB view
8k 1,356 85.3 17.9 GB view
16k 1,291 78.4 18.3 GB view
32k 1,113 68.7 19.1 GB view
64k 945.4 53.9 20.8 GB view
128k 695.9 39.1 24.4 GB current
Batching Results
Batch Size TG tok/s Speedup
91.6 1.00×
135.0 1.47×
269.4 2.94×