← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-04-28
Performance
16k
tokens
2,025
PP tok/s
54.0
TG tok/s
8092
TTFT (ms)
15.2
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 16,384
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 view
8k 2,082 62.4 14.8 GB view
16k 2,025 54.0 15.2 GB current
Batching Results
Batch Size TG tok/s Speedup
74.7 1.00×
106.1 1.42×
136.0 1.82×