← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 4bit · 2026-05-07
Performance
64k
tokens
1,271
PP tok/s
39.0
TG tok/s
51577
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,375 74.2 14.3 GB view
16k 1,757 61.6 15.4 GB view
64k 1,271 39.0 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
74.2 1.00×
101.2 1.36×
122.9 1.66×