← Back to community benchmarks

Qwopus3.5-9B-v3

M4 (10c) · 16 GB · 6bit · 2026-04-23
Performance
1k
tokens
197.7
PP tok/s
12.2
TG tok/s
5181
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 197.7 12.2 7.8 GB current
4k 201.2 12.8 8.3 GB view
8k 190.4 11.8 8.7 GB view
16k 193.5 13.1 9.5 GB view
Batching Results
Batch Size TG tok/s Speedup
12.2 1.00×
27.5 2.25×
30.5 2.50×