← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 6bit · 2026-04-16
Performance
1k
tokens
991.9
PP tok/s
68.0
TG tok/s
1032
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
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 991.9 68.0 20.2 GB current
4k 1,127 64.6 20.7 GB view
8k 1,182 55.6 20.9 GB view
16k 1,085 39.6 21.2 GB view
32k 1,035 25.6 22.1 GB view
Batching Results
Batch Size TG tok/s Speedup
68.0 1.00×
104.7 1.54×
137.5 2.02×
164.6 2.42×