← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-04-18
Performance
16k
tokens
246.9
PP tok/s
23.2
TG tok/s
66367
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 239.4 36.7 14.2 GB view
4k 254.1 34.9 14.7 GB view
8k 254.5 29.9 14.8 GB view
16k 246.9 23.2 15.2 GB current
Batching Results
Batch Size TG tok/s Speedup
36.7 1.00×
74.0 2.02×
148.5 4.05×