← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Max (24c) · 64 GB · 4bit · 2026-03-09
Performance
8k
tokens
438.8
PP tok/s
51.0
TG tok/s
18669
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 416.0 58.4 20.1 GB view
4k 446.3 55.7 20.2 GB view
8k 438.8 51.0 20.4 GB current
Batching Results
Batch Size TG tok/s Speedup
58.4 1.00×
78.9 1.35×
91.9 1.57×
105.2 1.80×