← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (20c) · 48 GB · 4bit · 2026-03-09
Performance
1k
tokens
821.5
PP tok/s
75.6
TG tok/s
1247
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 821.5 75.6 20.0 GB current
4k 879.6 79.1 20.2 GB view
8k 873.4 71.9 20.4 GB view
Batching Results
Batch Size TG tok/s Speedup
75.6 1.00×
129.0 1.71×
166.8 2.21×