← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Pro (14c) · 36 GB · 4bit · 2026-03-15
Performance
8k
tokens
539.2
PP tok/s
48.8
TG tok/s
15192
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 552.8 54.9 20.1 GB view
4k 561.7 52.4 20.2 GB view
8k 539.2 48.8 20.4 GB current
16k 494.0 43.1 20.8 GB view
32k 428.5 29.3 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
54.9 1.00×
86.0 1.57×
171.9 3.13×