← Back to community benchmarks

Qwen3.5-9b-Sushi-Coder-RL

M5 (10c) · 32 GB · 4bit · 2026-05-04
Performance
8k
tokens
386.5
PP tok/s
89.2
TG tok/s
21195
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 642.8 101.3 8.1 GB view
4k 454.3 95.1 9.4 GB view
8k 386.5 89.2 9.7 GB current
16k 1,362 20.4 7.8 GB view
32k 1,546 16.7 8.6 GB view
64k 1,244 17.9 9.7 GB view
128k 856.5 14.8 12.0 GB view