← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 64 GB · 4bit · 2026-05-14
Performance
1k
tokens
2,221
PP tok/s
112.3
TG tok/s
461
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,221 112.3 14.3 GB current
4k 2,067 103.8 14.9 GB view
8k 2,584 99.1 15.1 GB view
16k 2,602 91.7 15.6 GB view
32k 2,450 78.7 16.5 GB view
64k 2,027 59.9 18.5 GB view
128k 1,408 38.9 22.7 GB view
Batching Results
Batch Size TG tok/s Speedup
112.3 1.00×
159.1 1.42×
193.5 1.72×