← Back to community benchmarks

Qwen3.5-9B

M1 (7c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
67.8
PP tok/s
10.9
TG tok/s
60370
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 68.7 11.9 6.5 GB view
4k 67.8 10.9 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
11.9 1.00×
10.3 0.87×
9.0 0.76×