← Back to community benchmarks

gemma-4-26B-A4B-it-qat

M3 Pro (14c) · 36 GB · 4bit · 2026-07-25
Performance
16k
tokens
412.0
PP tok/s
33.9
TG tok/s
39768
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.5.3
macOS macOS 27.0
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 453.1 36.7 14.3 GB view
4k 442.5 35.8 14.7 GB view
8k 426.5 36.1 14.8 GB view
16k 412.0 33.9 15.2 GB current
32k 336.8 15.2 16.0 GB view
64k 277.8 24.8 17.7 GB view
Batching Results
Batch Size TG tok/s Speedup
36.7 1.00×
80.3 2.19×
138.4 3.77×