← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-18
Performance
64k
tokens
2,390
PP tok/s
58.6
TG tok/s
27420
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,258 117.1 14.3 GB view
4k 3,362 111.1 14.9 GB view
8k 3,676 104.3 15.1 GB view
16k 3,655 93.2 15.6 GB view
32k 3,170 77.0 16.0 GB view
64k 2,390 58.6 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
117.1 1.00×
168.7 1.44×