← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
655.8
PP tok/s
34.3
TG tok/s
24983
TTFT (ms)
124.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 673.7 | 41.4 | 123.2 GB | view |
| 4k | 707.5 | 39.8 | 123.5 GB | view |
| 8k | 691.6 | 37.1 | 123.9 GB | view |
| 16k | 655.8 | 34.3 | 124.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.4 | 1.00× |
| 2× | 67.0 | 1.62× |
| 4× | 92.0 | 2.22× |