← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-07-21
Performance
32k
tokens
1,806
PP tok/s
51.2
TG tok/s
18145
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,276 78.4 14.0 GB view
4k 2,218 74.9 14.5 GB view
8k 2,149 69.8 15.3 GB view
16k 2,044 62.3 16.0 GB view
32k 1,806 51.2 18.3 GB current
64k 1,339 37.5 18.3 GB view
128k 884.1 23.0 23.3 GB view
195k 619.2 17.2 27.4 GB view
Batching Results
Batch Size TG tok/s Speedup
78.4 1.00×
120.1 1.53×
160.9 2.05×
305.0 3.89×