← Back to community benchmarks

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

M2 Pro (16c) · 32 GB · 5bit · 2026-05-14
Performance
32k
tokens
391.6
PP tok/s
25.1
TG tok/s
83685
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 428.8 33.8 17.4 GB view
4k 464.3 33.3 17.9 GB view
8k 460.0 31.8 18.2 GB view
16k 438.9 29.7 18.7 GB view
32k 391.6 25.1 19.6 GB current
64k 316.4 18.2 20.8 GB view
Batching Results
Batch Size TG tok/s Speedup
33.8 1.00×
43.9 1.30×
87.7 2.59×