← Back to community benchmarks

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

M1 Max (32c) · 32 GB · 5bit · 2026-04-27
Performance
16k
tokens
1,332
PP tok/s
39.9
TG tok/s
12296
TTFT (ms)
9.2
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 16,384
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 view
16k 1,332 39.9 9.2 GB current