← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-03-11
Performance
1k
tokens
1,655
PP tok/s
84.1
TG tok/s
619
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 15.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,655 84.1 36.2 GB current
4k 1,703 80.1 36.3 GB view
Batching Results
Batch Size TG tok/s Speedup
84.1 1.00×
137.7 1.64×
202.0 2.40×