← Back to community benchmarks

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

M4 (10c) · 32 GB · 4bit · 2026-05-07
Performance
32k
tokens
288.0
PP tok/s
20.7
TG tok/s
113785
TTFT (ms)
16.9
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 336.0 25.8 14.7 GB view
4k 347.9 27.1 15.3 GB view
8k 362.5 26.1 15.4 GB view
16k 337.3 23.8 16.0 GB view
32k 288.0 20.7 16.9 GB current
64k 223.7 11.8 18.1 GB view
Batching Results
Batch Size TG tok/s Speedup
25.8 1.00×
38.6 1.50×
46.4 1.80×