← Back to community benchmarks

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

M2 Pro (16c) · 32 GB · 5bit · 2026-05-15
Performance
8k
tokens
458.7
PP tok/s
32.5
TG tok/s
17860
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.9.dev2
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 433.4 34.3 17.4 GB view
4k 461.7 33.6 18.1 GB view
8k 458.7 32.5 18.2 GB current
16k 432.4 30.2 18.7 GB view
32k 388.7 26.9 19.6 GB view
64k 324.7 22.1 21.6 GB view