← Back to community benchmarks

Huihui-Qwen3.5-35B-A3B-abliterated

M4 Pro (20c) · 48 GB · 4bit · 2026-03-10
Performance
4k
tokens
772.3
PP tok/s
77.0
TG tok/s
5303
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 689.6 83.7 19.2 GB view
4k 772.3 77.0 19.6 GB current
Batching Results
Batch Size TG tok/s Speedup
83.7 1.00×
127.9 1.53×
258.2 3.08×