← Back to community benchmarks
Qwopus3.5-9B-v3
Performance
1k
tokens
586.0
PP tok/s
47.7
TG tok/s
1748
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 586.0 | 47.7 | 7.8 GB | current |
| 4k | 646.6 | 46.5 | 8.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.7 | 1.00× |
| 2× | 82.5 | 1.73× |
| 4× | 90.6 | 1.90× |