← Back to community benchmarks

gemma-4-E4B-it-heretic-oQ6

M3 (10c) · 16 GB · 6bit · 2026-05-18
Performance
1k
tokens
525.8
PP tok/s
50.0
TG tok/s
1948
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 525.8 50.0 6.9 GB current
4k 526.0 47.4 7.0 GB view
8k 502.7 42.2 7.2 GB view
16k 444.4 36.3 7.4 GB view
32k 276.1 16.5 8.0 GB view
64k 175.7 10.9 9.2 GB view
Batching Results
Batch Size TG tok/s Speedup
50.0 1.00×
18.6 0.37×
22.4 0.45×