← Back to community benchmarks

qwen3.5-35b

M4 Pro (20c) · 48 GB · 4bit · 2026-03-18
Performance
8k
tokens
575.8
PP tok/s
67.5
TG tok/s
14228
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.0
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 261.1 74.4 19.0 GB view
4k 605.4 71.6 18.7 GB view
8k 575.8 67.5 18.9 GB current
16k 541.1 61.2 19.1 GB view
32k 493.2 52.5 19.7 GB view