← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Max (38c) · 96 GB · 4bit · 2026-05-19
Performance
32k
tokens
574.2
PP tok/s
46.5
TG tok/s
57067
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 558.8 70.8 14.3 GB view
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 current
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×