← Back to community benchmarks

Qwen3.5-35B-A3B5.5bit

M1 Max (32c) · 32 GB · 5bit · 2026-03-09
Performance
4k
tokens
540.6
PP tok/s
53.5
TG tok/s
7576
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.0.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 450.2 58.4 23.2 GB view
4k 540.6 53.5 23.4 GB current
Batching Results
Batch Size TG tok/s Speedup
58.4 1.00×
81.0 1.39×
98.7 1.69×
110.8 1.90×