← Back to community benchmarks

gemma-4-26B-A4B-it-oQ4

M1 Max (32c) · 64 GB · 4bit · 2026-05-17
Performance
128k
tokens
414.2
PP tok/s
16.7
TG tok/s
316433
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 687.0 57.7 14.4 GB view
4k 788.2 55.2 15.1 GB view
8k 820.0 52.0 15.3 GB view
16k 790.9 47.5 15.7 GB view
32k 718.8 39.7 16.7 GB view
64k 596.1 26.1 18.7 GB view
128k 414.2 16.7 22.9 GB current
Batching Results
Batch Size TG tok/s Speedup
57.7 1.00×
78.0 1.35×
96.5 1.67×