← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
32k
tokens
519.9
PP tok/s
30.8
TG tok/s
63032
TTFT (ms)
38.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.5
macOS
macOS 26.2
Context
32,768