← Back to community benchmarks
CoPaw-Flash-9B-oQ4
Performance
4k
tokens
207.5
PP tok/s
20.1
TG tok/s
19741
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 210.9 | 20.3 | 5.7 GB | view |
| 4k | 207.5 | 20.1 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.3 | 1.00× |
| 2× | 38.9 | 1.92× |
| 4× | 77.4 | 3.81× |