← Back to community benchmarks

Qwopus3.5-9B-v3.5-oQ5

M1 Max (32c) · 32 GB · 5bit · 2026-04-27
Performance
8k
tokens
502.0
PP tok/s
46.5
TG tok/s
16320
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 353.4 111.9 10.3 GB view
4k 345.6 49.4 8.0 GB view
8k 502.0 46.5 8.4 GB current
16k 1,332 39.9 9.2 GB view