← Back to community benchmarks

Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-fp16

M4 Pro (20c) · 64 GB · fp16 · 2026-03-14
Performance
4k
tokens
495.3
PP tok/s
15.0
TG tok/s
8270
TTFT (ms)
18.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.11
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 472.8 15.2 18.3 GB view
4k 495.3 15.0 18.6 GB current
Batching Results
Batch Size TG tok/s Speedup
15.2 1.00×
15.0 0.99×
28.6 1.88×