← Back to community benchmarks

Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled

M1 (8c) · 16 GB · 4bit · 2026-03-12
Performance
4k
tokens
140.8
PP tok/s
20.4
TG tok/s
29100
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 136.4 21.4 3.3 GB view
4k 140.8 20.4 3.5 GB current
Batching Results
Batch Size TG tok/s Speedup
21.4 1.00×
33.3 1.56×
34.2 1.60×