← Back to community benchmarks

gemma-4-E4B-it-heretic-oQ6

M3 (10c) · 16 GB · 6bit · 2026-05-18
Performance
16k
tokens
433.1
PP tok/s
29.7
TG tok/s
37827
TTFT (ms)
7.4
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 523.5 48.8 6.9 GB view
4k 527.5 45.2 7.0 GB view
8k 496.6 42.4 7.2 GB view
16k 433.1 29.7 7.4 GB current
32k 237.7 17.2 8.0 GB view
64k 190.9 10.7 9.2 GB view
Batching Results
Batch Size TG tok/s Speedup
48.8 1.00×
14.8 0.30×
19.7 0.40×
22.2 0.45×