← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-05-06
Performance
8k
tokens
362.3
PP tok/s
29.4
TG tok/s
22609
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 359.1 31.8 14.2 GB view
4k 364.5 30.8 14.9 GB view
8k 362.3 29.4 15.0 GB current
16k 340.9 27.3 15.5 GB view
32k 303.1 23.0 15.9 GB view
64k 243.6 17.5 17.7 GB view
Batching Results
Batch Size TG tok/s Speedup
31.8 1.00×
48.8 1.53×
57.7 1.81×
66.6 2.09×