← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-12
Performance
32k
tokens
453.8
PP tok/s
36.4
TG tok/s
72207
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.5
Context 32,768
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 view
16k 484.1 44.6 15.6 GB view
32k 453.8 36.4 16.5 GB current
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×