← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-18
Performance
4k
tokens
71.7
PP tok/s
10.2
TG tok/s
57166
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 74.6 9.8 5.7 GB view
4k 71.7 10.2 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
9.8 1.00×
18.0 1.84×
19.2 1.96×