← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 64 GB · 8bit · 2026-03-09
Performance
1k
tokens
1,084
PP tok/s
68.2
TG tok/s
945
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
68.2 1.00×
120.2 1.76×
183.3 2.69×
265.6 3.89×