← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 64 GB · 6bit · 2026-05-06
Performance
16k
tokens
1,302
PP tok/s
75.4
TG tok/s
12581
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,078 88.1 20.0 GB view
4k 1,350 84.6 20.6 GB view
8k 1,383 81.1 20.8 GB view
16k 1,302 75.4 21.3 GB current
32k 1,127 65.7 22.2 GB view
64k 960.4 52.7 24.3 GB view
Batching Results
Batch Size TG tok/s Speedup
88.1 1.00×
100.4 1.14×
159.1 1.81×
189.0 2.15×