← Back to community benchmarks

gemma-4-26B-A4B-it

M5 (10c) · 24 GB · 4bit · 2026-05-19
Performance
1k
tokens
736.0
PP tok/s
41.0
TG tok/s
1391
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 24 GB
GPU Cores 10
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 736.0 41.0 14.2 GB current
4k 910.3 39.0 14.9 GB view
Batching Results
Batch Size TG tok/s Speedup
41.0 1.00×
61.1 1.49×
72.3 1.76×