← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-04-15
Performance
4k
tokens
3,766
PP tok/s
121.5
TG tok/s
1088
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,239 124.6 18.3 GB view
4k 3,766 121.5 19.1 GB current
Batching Results
Batch Size TG tok/s Speedup
124.6 1.00×
214.9 1.72×
320.4 2.57×