← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-oQ5

M4 Pro (20c) · 64 GB · 5bit · 2026-05-06
Performance
8k
tokens
652.3
PP tok/s
49.4
TG tok/s
12559
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 675.8 52.8 17.4 GB view
4k 715.8 51.7 17.8 GB view
8k 652.3 49.4 18.2 GB current
16k 589.1 45.8 18.3 GB view
32k 537.7 37.4 19.6 GB view
64k 451.1 30.6 20.8 GB view
128k 332.7 19.2 24.4 GB view
Batching Results
Batch Size TG tok/s Speedup
52.8 1.00×
77.1 1.46×
154.2 2.92×