← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-04-28
Performance
4k
tokens
1,994
PP tok/s
70.7
TG tok/s
2054
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,490 74.7 14.3 GB view
4k 1,994 70.7 14.7 GB current
8k 2,082 62.4 14.8 GB view
16k 2,025 54.0 15.2 GB view
Batching Results
Batch Size TG tok/s Speedup
74.7 1.00×
106.1 1.42×
136.0 1.82×