← Back to community benchmarks

gemma-4-26b-a4b-it

M5 (10c) · 32 GB · 4bit · 2026-05-14
Performance
16k
tokens
998.2
PP tok/s
32.8
TG tok/s
16414
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 742.7 41.1 14.2 GB view
4k 915.2 38.9 14.9 GB view
8k 1,038 36.5 15.0 GB view
16k 998.2 32.8 15.2 GB current
32k 872.4 27.3 15.9 GB view
64k 679.7 20.2 17.7 GB view
128k 461.3 12.9 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
41.1 1.00×
59.1 1.44×
72.4 1.76×