← Back to community benchmarks

Qwen3.5-35B-A3B

M4 (10c) · 32 GB · 4bit · 2026-03-10
Performance
32k
tokens
321.0
PP tok/s
25.1
TG tok/s
102076
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.0.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 441.4 47.1 20.0 GB view
4k 448.2 43.7 20.2 GB view
8k 437.6 40.6 20.4 GB view
16k 395.9 34.3 20.8 GB view
32k 321.0 25.1 21.6 GB current
64k 238.7 17.6 23.3 GB view
Batching Results
Batch Size TG tok/s Speedup
47.1 1.00×
71.6 1.52×
81.5 1.73×