← Back to community benchmarks
Qwen3.5-9B-DeepSeek-V4-Flash
Performance
16k
tokens
1,431
PP tok/s
29.5
TG tok/s
11448
TTFT (ms)
12.0
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