← Back to community benchmarks

Qwen3.5-9B8bit-mtp

M4 Pro (16c) · 24 GB · 8bit · 2026-05-12
Performance
1k
tokens
338.1
PP tok/s
27.8
TG tok/s
3029
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 338.1 27.8 9.9 GB current
4k 354.6 27.3 10.6 GB view