← Back to community benchmarks

gemma-4-26B-A4B-it-oQ8e

M4 Max (40c) · 64 GB · 8bit · 2026-04-28
Performance
4k
tokens
1,313
PP tok/s
72.2
TG tok/s
3121
TTFT (ms)
26.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8.dev3
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,156 75.3 25.8 GB view
4k 1,313 72.2 26.1 GB current
8k 1,187 67.6 26.3 GB view
16k 1,005 57.8 26.7 GB view
Batching Results
Batch Size TG tok/s Speedup
75.3 1.00×
110.3 1.46×
141.3 1.88×
170.6 2.27×