← Back to community benchmarks

Huihui-Qwen3.5-9B-abliterated

M1 (8c) · 16 GB · 4bit · 2026-04-16
Performance
4k
tokens
78.7
PP tok/s
12.3
TG tok/s
52061
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 77.5 12.6 5.7 GB view
4k 78.7 12.3 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
12.6 1.00×
18.8 1.49×
19.3 1.53×