← Back to community benchmarks
Qwen3.5-9b-Sushi-Coder-RL
Performance
4k
tokens
108.5
PP tok/s
18.3
TG tok/s
37737
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 107.0 | 19.2 | 5.7 GB | view |
| 4k | 108.5 | 18.3 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.2 | 1.00× |
| 2× | 38.1 | 1.98× |
| 4× | 73.8 | 3.84× |