← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 64 GB · 4bit · 2026-05-03
Performance
64k
tokens
296.0
PP tok/s
19.9
TG tok/s
221382
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 348.1 48.3 14.3 GB view
4k 371.0 45.9 14.9 GB view
8k 373.6 43.4 15.1 GB view
16k 364.8 39.1 15.6 GB view
32k 338.3 30.9 16.5 GB view
64k 296.0 19.9 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
48.3 1.00×
61.3 1.27×
71.2 1.47×
79.2 1.64×