← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
1,357
PP tok/s
104.5
TG tok/s
754
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,357 | 104.5 | 6.7 GB | current |
| 4k | 1,461 | 99.4 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.5 | 1.00× |
| 2× | 178.8 | 1.71× |
| 4× | 244.8 | 2.34× |
| 8× | 306.4 | 2.93× |