← Back to community benchmarks

gemma-4-26B-A4B-it-5bit-DWQ

M2 Pro (16c) · 32 GB · 5bit · 2026-04-17
Performance
4k
tokens
269.9
PP tok/s
32.6
TG tok/s
15178
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 254.5 34.7 16.9 GB view
4k 269.9 32.6 17.4 GB current
8k 269.1 27.5 17.5 GB view
16k 261.4 21.8 17.9 GB view
32k 244.8 11.7 18.6 GB view
Batching Results
Batch Size TG tok/s Speedup
34.7 1.00×
40.2 1.16×
44.0 1.27×
49.7 1.43×