← Back to community benchmarks

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled

M1 Pro (16c) · 32 GB · 4bit · 2026-03-11
Performance
16k
tokens
154.4
PP tok/s
14.3
TG tok/s
106124
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 153.7 33.3 5.8 GB view
16k 154.4 14.3 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 33.3 1.00×
2× 25.0 0.75×