← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-heretic-ara8bit-int8-affine

M3 Ultra (60c) · 256 GB · 8bit · 2026-06-02
Performance
4k
tokens
1,679
PP tok/s
78.6
TG tok/s
2439
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,315 80.9 27.2 GB view
4k 1,679 78.6 27.6 GB current
8k 1,730 74.7 27.7 GB view
16k 1,667 69.2 28.1 GB view
32k 1,513 59.8 28.9 GB view
64k 1,238 46.0 30.6 GB view
128k 889.5 30.8 34.2 GB view
Batching Results
Batch Size TG tok/s Speedup
80.9 1.00×
117.2 1.45×
162.0 2.00×
223.5 2.76×