← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
681.8
PP tok/s
35.2
TG tok/s
24029
TTFT (ms)
126.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 675.2 | 40.6 | 123.3 GB | view |
| 4k | 738.8 | 40.4 | 124.8 GB | view |
| 8k | 726.8 | 36.7 | 125.4 GB | view |
| 16k | 681.8 | 35.2 | 126.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.6 | 1.00× |
| 2× | 65.5 | 1.61× |
| 4× | 90.2 | 2.22× |