← Back to community benchmarks
Qwen3.5-9B-DeepSeek-V4-Flash
Performance
8k
tokens
737.4
PP tok/s
13.8
TG tok/s
11110
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 642.4 | 14.7 | 9.8 GB | view |
| 4k | 733.1 | 14.4 | 10.4 GB | view |
| 8k | 737.4 | 13.8 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.7 | 1.00× |
| 2× | 29.2 | 1.99× |