← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 64 GB · 8bit · 2026-04-12
Performance
64k
tokens
2,489
PP tok/s
54.2
TG tok/s
26330
TTFT (ms)
31.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,115 85.6 25.7 GB view
4k 3,146 81.9 26.6 GB view
8k 3,316 78.5 27.0 GB view
16k 3,351 74.7 27.6 GB view
32k 3,146 66.1 28.9 GB view
64k 2,489 54.2 31.5 GB current
128k 1,608 39.9 37.2 GB view
Batching Results
Batch Size TG tok/s Speedup
85.6 1.00×
124.5 1.45×
167.6 1.96×
216.2 2.53×