← Back to community benchmarks
Qwopus3.5-9B-v3
Performance
4k
tokens
174.1
PP tok/s
34.4
TG tok/s
23530
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 169.3 | 36.1 | 5.8 GB | view |
| 4k | 174.1 | 34.4 | 6.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.1 | 1.00× |
| 2× | 40.8 | 1.13× |
| 4× | 42.1 | 1.17× |