← Back to community benchmarks

Qwen3.5-35B-A3B4.8-bit

M1 Max (24c) · 32 GB · 4bit · 2026-03-11
Performance
8k
tokens
435.2
PP tok/s
46.3
TG tok/s
18824
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.7
macOS macOS 15.6
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 394.2 56.3 20.4 GB view
4k 436.8 53.4 20.5 GB view
8k 435.2 46.3 20.7 GB current
Batching Results
Batch Size TG tok/s Speedup
56.3 1.00×
79.4 1.41×
159.2 2.83×
314.4 5.58×