← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 256 GB · unknown · 2026-05-07
Performance
64k
tokens
1,196
PP tok/s
39.7
TG tok/s
54808
TTFT (ms)
52.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.3
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,224 64.5 47.8 GB view
4k 1,560 62.6 48.5 GB view
8k 1,604 60.6 48.6 GB view
16k 1,578 56.6 49.1 GB view
32k 1,445 49.9 50.0 GB view
64k 1,196 39.7 52.0 GB current
Batching Results
Batch Size TG tok/s Speedup
64.5 1.00×
57.2 0.89×
97.1 1.51×
82.9 1.29×