← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 6bit · 2026-04-16
Performance
1k
tokens
638.6
PP tok/s
42.1
TG tok/s
1604
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 638.6 42.1 20.1 GB current
4k 630.5 38.7 20.6 GB view
8k 583.6 33.8 20.7 GB view
16k 536.9 23.9 21.1 GB view
32k 479.9 14.5 21.9 GB view
64k 397.5 8.2 23.6 GB view
Batching Results
Batch Size TG tok/s Speedup
42.1 1.00×
59.7 1.42×
62.2 1.48×
75.0 1.78×