← Back to community benchmarks

gemma-4-26b-a4b-it-mxfp8

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-15
Performance
16k
tokens
1,633
PP tok/s
53.8
TG tok/s
10034
TTFT (ms)
26.1
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.4
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,318 78.8 25.0 GB view
4k 1,633 74.0 25.5 GB view
8k 1,680 65.3 25.8 GB view
16k 1,633 53.8 26.1 GB current