← Back to community benchmarks

unsloth:gemma-4-26b-a4b-it

M5 Max (40c) · 64 GB · 8bit · 2026-07-19
Performance
32k
tokens
2,588
PP tok/s
64.8
TG tok/s
12664
TTFT (ms)
28.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,481 83.2 25.8 GB view
4k 2,795 79.9 26.1 GB view
8k 3,034 77.9 26.9 GB view
16k 2,879 73.2 26.9 GB view
32k 2,588 64.8 28.1 GB current
64k 2,076 52.9 30.5 GB view
Batching Results
Batch Size TG tok/s Speedup
83.2 1.00×
135.1 1.62×
198.4 2.38×
273.6 3.29×