← Back to community benchmarks

gemma-4-E2B-it-oQ8

M2 Max (38c) · 96 GB · 8bit · 2026-06-04
Performance
1k
tokens
3,658
PP tok/s
80.9
TG tok/s
280
TTFT (ms)
5.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.4.1
macOS macOS 15.7.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,658 80.9 5.5 GB current
4k 3,641 80.0 5.6 GB view
8k 3,433 75.9 5.6 GB view
16k 3,380 74.1 5.7 GB view
32k 3,085 64.2 6.0 GB view
64k 2,542 57.0 6.7 GB view
Batching Results
Batch Size TG tok/s Speedup
80.9 1.00×
153.4 1.90×
221.3 2.74×
451.9 5.59×