← Back to community benchmarks

Qwen3.5-35B-A3B-Text-qx64-hi

M1 Max (24c) · 64 GB · 6bit · 2026-03-12
Performance
16k
tokens
408.0
PP tok/s
39.2
TG tok/s
40154
TTFT (ms)
26.0
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 351.5 51.3 25.2 GB view
4k 424.5 49.4 25.4 GB view
8k 423.7 46.4 25.6 GB view
16k 408.0 39.2 26.0 GB current
32k 373.7 30.2 26.8 GB view
64k 312.2 20.9 28.5 GB view
Batching Results
Batch Size TG tok/s Speedup
51.3 1.00×
69.8 1.36×
84.2 1.64×
99.3 1.94×