← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 24 GB · 4bit · 2026-05-17
Performance
64k
tokens
1,168
PP tok/s
38.0
TG tok/s
56101
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,339 70.1 14.3 GB view
4k 1,656 67.1 14.9 GB view
64k 1,168 38.0 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
70.1 1.00×
95.5 1.36×
121.5 1.73×