← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-05
Performance
1k
tokens
322.3
PP tok/s
45.9
TG tok/s
3178
TTFT (ms)
14.2
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 322.3 45.9 14.2 GB current
4k 364.6 42.7 14.7 GB view
Batching Results
Batch Size TG tok/s Speedup
45.9 1.00×
60.3 1.31×
55.8 1.22×