← Back to community benchmarks

Qwopus3.5-9B-v3-HLWQ

M3 (8c) · 16 GB · 4bit · 2026-04-17
Performance
1k
tokens
147.8
PP tok/s
19.6
TG tok/s
6930
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M3 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 147.8 19.6 5.7 GB current
4k 151.1 19.1 6.3 GB view
8k 148.6 18.3 6.7 GB view
16k 114.9 11.1 7.4 GB view
Batching Results
Batch Size TG tok/s Speedup
19.6 1.00×
24.1 1.23×
26.4 1.35×
29.9 1.53×