← Back to community benchmarks
qwen35-9b
Performance
1k
tokens
101.4
PP tok/s
8.0
TG tok/s
10098
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 101.4 | 8.0 | 6.5 GB | current |
| 4k | 99.8 | 7.8 | 6.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.0 | 1.00× |
| 2× | 13.2 | 1.65× |
| 4× | 41.7 | 5.21× |