← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
16k
tokens
1,169
PP tok/s
42.6
TG tok/s
14020
TTFT (ms)
83.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,162 | 54.2 | 80.6 GB | view |
| 4k | 1,466 | 52.0 | 82.1 GB | view |
| 16k | 1,169 | 42.6 | 83.9 GB | current |
| 32k | 992.3 | 34.3 | 86.3 GB | view |
| 64k | 701.6 | 22.4 | 91.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.2 | 1.00× |
| 2× | 63.3 | 1.17× |
| 4× | 71.1 | 1.31× |