← Back to community benchmarks

Qwen3.5-9B

M1 (7c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
66.8
PP tok/s
11.5
TG tok/s
61286
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 69.2 11.8 6.5 GB view
4k 66.8 11.5 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
11.8 1.00×
16.1 1.36×
15.4 1.31×