← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 6bit · 2026-04-25
Performance
16k
tokens
333.3
PP tok/s
16.8
TG tok/s
49159
TTFT (ms)
20.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.5.dev1
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 354.6 26.2 19.9 GB view
4k 364.4 25.2 20.4 GB view
8k 354.6 21.7 20.4 GB view
16k 333.3 16.8 20.9 GB current
Batching Results
Batch Size TG tok/s Speedup
26.2 1.00×
37.5 1.43×
41.5 1.58×
48.5 1.85×