← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M5 Max (40c) · 128 GB · 4bit · 2026-05-11
Performance
8k
tokens
3,602
PP tok/s
95.4
TG tok/s
2275
TTFT (ms)
16.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,248 104.4 15.2 GB view
4k 3,387 100.0 15.7 GB view
8k 3,602 95.4 16.2 GB current
16k 3,548 87.1 16.6 GB view
32k 3,202 76.7 17.4 GB view
64k 2,542 60.6 19.4 GB view
128k 1,758 42.9 23.5 GB view
Batching Results
Batch Size TG tok/s Speedup
104.4 1.00×
151.7 1.45×
214.7 2.06×
435.1 4.17×