← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
1,504
PP tok/s
60.2
TG tok/s
5449
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.23
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 898.7 | 65.3 | 65.6 GB | view |
| 4k | 1,423 | 60.5 | 67.0 GB | view |
| 8k | 1,504 | 60.2 | 67.7 GB | current |
| 16k | 1,382 | 53.1 | 68.9 GB | view |
| 32k | 1,152 | 43.3 | 71.2 GB | view |
| 64k | 829.4 | 30.1 | 76.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.3 | 1.00× |
| 2× | 94.5 | 1.45× |
| 4× | 120.9 | 1.85× |