← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 256 GB · 4bit · 2026-05-19
Performance
4k
tokens
1,677
PP tok/s
102.1
TG tok/s
2443
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,290 107.0 14.3 GB view
4k 1,677 102.1 15.0 GB current
8k 1,720 93.2 15.3 GB view
16k 1,684 84.7 15.8 GB view
32k 1,519 70.6 16.7 GB view
64k 1,238 51.0 18.7 GB view
Batching Results
Batch Size TG tok/s Speedup
107.0 1.00×
151.0 1.41×
210.6 1.97×
279.8 2.61×