← Back to community benchmarks

Qwen3.6-35B-A3B

M4 (10c) · 32 GB · 4bit · 2026-04-29
Performance
1k
tokens
161.9
PP tok/s
36.8
TG tok/s
6323
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 161.9 36.8 20.5 GB current
4k 238.6 44.8 19.9 GB view