← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-12
Performance
8k
tokens
493.9
PP tok/s
49.5
TG tok/s
16588
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 439.2 55.5 14.3 GB view
4k 488.3 52.8 14.9 GB view
8k 493.9 49.5 15.1 GB current
16k 484.1 44.6 15.6 GB view
32k 453.8 36.4 16.5 GB view
64k 396.8 22.7 17.7 GB view
128k 296.0 14.5 21.2 GB view
195k 226.3 10.1 25.0 GB view
Batching Results
Batch Size TG tok/s Speedup
55.5 1.00×
74.3 1.34×
89.2 1.61×
101.7 1.83×