← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 64 GB · 4bit · 2026-04-17
Performance
8k
tokens
370.4
PP tok/s
38.2
TG tok/s
22117
TTFT (ms)
17.2
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 342.9 47.6 16.7 GB view
4k 366.0 44.0 17.1 GB view
8k 370.4 38.2 17.2 GB current
Batching Results
Batch Size TG tok/s Speedup
47.6 1.00×
59.9 1.26×