← Back to community benchmarks

Qwen3.5-35B-A3B5.5bit

M4 (10c) · 32 GB · 5bit · 2026-03-10
Performance
8k
tokens
413.0
PP tok/s
36.5
TG tok/s
19835
TTFT (ms)
23.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
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 396.1 40.5 23.2 GB view
4k 432.5 38.9 23.4 GB view
8k 413.0 36.5 23.6 GB current
16k 369.3 31.6 24.0 GB view