← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-17
Performance
8k
tokens
2,110
PP tok/s
75.2
TG tok/s
3883
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.6
macOS macOS 15.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,479 95.2 14.2 GB view
4k 2,023 86.5 14.7 GB view
8k 2,110 75.2 14.8 GB current
16k 2,088 61.2 15.2 GB view
32k 1,881 43.2 16.0 GB view
64k 1,467 25.2 17.7 GB view
128k 1,022 14.8 21.2 GB view
195k 751.4 10.0 24.8 GB view
Batching Results
Batch Size TG tok/s Speedup
95.2 1.00×
139.4 1.46×
222.0 2.33×
302.5 3.18×