← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
236.2
PP tok/s
40.3
TG tok/s
34688
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 235.7 | 46.4 | 6.7 GB | view |
| 4k | 238.8 | 44.0 | 7.0 GB | view |
| 8k | 236.2 | 40.3 | 7.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.4 | 1.00× |
| 2× | 52.2 | 1.12× |
| 4× | 54.6 | 1.18× |