← Back to community benchmarks
QwenPaw-Flash-9B-oQ4
Performance
32k
tokens
302.1
PP tok/s
42.3
TG tok/s
108454
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 306.9 | 60.8 | 5.9 GB | view |
| 4k | 322.5 | 58.1 | 6.5 GB | view |
| 8k | 322.2 | 55.7 | 6.9 GB | view |
| 16k | 316.0 | 50.3 | 7.7 GB | view |
| 32k | 302.1 | 42.3 | 9.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.8 | 1.00× |
| 2× | 70.8 | 1.16× |
| 4× | 76.2 | 1.25× |