← Back to community benchmarks
Qwen3.5-9B-DeepSeek-V4-Flash-oQ8-mtp
Performance
16k
tokens
1,418
PP tok/s
36.5
TG tok/s
11552
TTFT (ms)
12.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
16,384