← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-qx86-hi

M4 Max (40c) · 128 GB · 8bit · 2026-03-12
Performance
4k
tokens
1,576
PP tok/s
82.3
TG tok/s
2599
TTFT (ms)
33.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
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 1,202 87.0 33.3 GB view
4k 1,576 82.3 33.5 GB current
8k 1,588 80.8 33.7 GB view
Batching Results
Batch Size TG tok/s Speedup
87.0 1.00×
138.8 1.60×
197.3 2.27×
244.6 2.81×