← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
655.6
PP tok/s
33.4
TG tok/s
24992
TTFT (ms)
96.1
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 | 662.6 | 45.3 | 94.8 GB | view |
| 4k | 704.4 | 43.3 | 95.1 GB | view |
| 8k | 694.2 | 40.1 | 95.4 GB | view |
| 16k | 655.6 | 33.4 | 96.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.3 | 1.00× |
| 2× | 68.6 | 1.51× |
| 4× | 89.5 | 1.98× |