← Back to community benchmarks

Qwen3.5-9B

M5 (8c) · 16 GB · 4bit · 2026-05-04
Performance
1k
tokens
581.2
PP tok/s
27.1
TG tok/s
1762
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M5 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 581.2 27.1 5.7 GB current
4k 626.3 26.5 6.3 GB view
Batching Results
Batch Size TG tok/s Speedup
27.1 1.00×
51.5 1.90×
59.7 2.20×