← Back to community benchmarks

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

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-15
Performance
4k
tokens
2,642
PP tok/s
71.6
TG tok/s
1551
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 15.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,514 73.6 36.2 GB view
4k 2,642 71.6 36.3 GB current
Batching Results
Batch Size TG tok/s Speedup
73.6 1.00×
129.9 1.76×
216.1 2.94×