← Back to community benchmarks

gemma-4-26b-a4b

M3 Ultra (60c) · 256 GB · bf16 · 2026-05-08
Performance
16k
tokens
1,540
PP tok/s
56.7
TG tok/s
10639
TTFT (ms)
48.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 316.7 63.4 48.3 GB view
8k 1,575 61.1 48.6 GB view
16k 1,540 56.7 48.7 GB current
32k 1,415 49.8 49.5 GB view
64k 1,175 39.0 51.2 GB view
128k 856.4 26.6 54.8 GB view