← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
16k
tokens
1,354
PP tok/s
47.8
TG tok/s
12102
TTFT (ms)
83.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,010 | 58.8 | 79.8 GB | view |
| 4k | 1,450 | 56.3 | 81.3 GB | view |
| 8k | 1,472 | 53.4 | 81.9 GB | view |
| 16k | 1,354 | 47.8 | 83.1 GB | current |
| 32k | 1,139 | 39.3 | 85.5 GB | view |
| 64k | 878.8 | 29.6 | 90.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.8 | 1.00× |
| 2× | 92.4 | 1.57× |
| 4× | 107.2 | 1.82× |
| 8× | 123.0 | 2.09× |