← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 64 GB · 4bit · 2026-05-11
Performance
64k
tokens
509.7
PP tok/s
37.7
TG tok/s
128590
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 692.0 67.4 14.3 GB view
4k 737.6 64.8 14.9 GB view
8k 741.4 61.7 15.1 GB view
16k 688.9 57.0 15.6 GB view
32k 602.5 48.1 16.5 GB view
64k 509.7 37.7 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
67.4 1.00×
95.3 1.41×