← Back to community benchmarks

Qwen3.5-9B-unslothoQ4

M1 Max (32c) · 32 GB · 4bit · 2026-04-15
Performance
1k
tokens
257.2
PP tok/s
97.1
TG tok/s
3981
TTFT (ms)
11.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 257.2 97.1 11.6 GB current
4k 289.1 43.7 11.8 GB view
8k 306.3 40.4 12.1 GB view