← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8-fp16-mtp

M1 Ultra (64c) · 128 GB · 8bit · 2026-05-11
Performance
16k
tokens
1,759
PP tok/s
65.1
TG tok/s
9317
TTFT (ms)
38.2
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,156 71.1 36.2 GB view
4k 1,739 67.1 37.0 GB view
8k 1,814 66.1 37.3 GB view
16k 1,759 65.1 38.2 GB current
Batching Results
Batch Size TG tok/s Speedup
71.1 1.00×
104.6 1.47×
159.2 2.24×