← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
430.5
PP tok/s
32.5
TG tok/s
38062
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 435.2 | 45.5 | 66.3 GB | view |
| 4k | 458.3 | 43.5 | 66.7 GB | view |
| 8k | 459.2 | 40.2 | 67.0 GB | view |
| 16k | 430.5 | 32.5 | 67.7 GB | current |
| 32k | 368.8 | 23.0 | 69.1 GB | view |
| 64k | 318.7 | 15.3 | 71.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.5 | 1.00× |
| 8× | 130.5 | 2.87× |