← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-05
Performance
4k
tokens
364.6
PP tok/s
42.7
TG tok/s
11236
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.3
macOS macOS 14.7.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 322.3 45.9 14.2 GB view
4k 364.6 42.7 14.7 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 45.9 1.00×
2× 60.3 1.31×
4× 55.8 1.22×