← Back to community benchmarks

Huihui-Qwen3.5-35B-A3B-abliterated-8bit

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-15
Performance
1k
tokens
2,515
PP tok/s
73.3
TG tok/s
407
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 15.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,515 73.3 36.2 GB current
4k 2,667 70.8 36.3 GB view
8k 2,607 68.1 36.5 GB view
16k 2,399 62.2 37.0 GB view
Batching Results
Batch Size TG tok/s Speedup
73.3 1.00×
128.6 1.75×
208.9 2.85×
322.9 4.41×