← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 4bit · 2026-05-04
Performance
195k
tokens
413.9
PP tok/s
17.5
TG tok/s
483195
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,098 99.4 14.3 GB view
4k 1,321 98.9 14.9 GB view
8k 1,383 92.8 15.1 GB view
16k 1,274 83.8 15.8 GB view
32k 1,068 68.8 16.5 GB view
64k 868.9 52.0 17.7 GB view
128k 546.2 29.4 21.2 GB view
195k 413.9 17.5 25.0 GB current
Batching Results
Batch Size TG tok/s Speedup
99.4 1.00×
149.5 1.50×
172.5 1.74×
193.2 1.94×