← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M4 Max (40c) · 128 GB · 6bit · 2026-05-04
Performance
16k
tokens
1,439
PP tok/s
74.0
TG tok/s
11386
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,156 84.4 20.2 GB view
4k 1,417 83.1 20.7 GB view
8k 1,494 79.3 21.1 GB view
16k 1,439 74.0 21.2 GB current
32k 1,299 64.0 22.4 GB view
64k 1,069 50.3 23.6 GB view
Batching Results
Batch Size TG tok/s Speedup
84.4 1.00×
122.5 1.45×
160.3 1.90×