← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Ultra (48c) · 64 GB · 4bit · 2026-05-20
Performance
1k
tokens
585.0
PP tok/s
65.7
TG tok/s
1750
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 64 GB
GPU Cores 48
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 585.0 65.7 18.2 GB current
4k 867.7 62.6 19.0 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 65.7 1.00×
2× 105.0 1.60×
4× 144.8 2.20×