← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Max (38c) · 96 GB · 4bit · 2026-05-19
Performance
1k
tokens
558.8
PP tok/s
70.8
TG tok/s
1832
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 558.8 70.8 14.3 GB current
4k 623.3 66.6 14.9 GB view
8k 627.9 62.8 15.1 GB view
16k 615.2 56.6 15.6 GB view
32k 574.2 46.5 16.5 GB view
64k 505.0 34.8 18.5 GB view
128k 403.9 22.7 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
70.8 1.00×
95.8 1.35×
113.6 1.60×