← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
32k
tokens
1,080
PP tok/s
43.6
TG tok/s
30328
TTFT (ms)
71.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,015 | 63.2 | 65.6 GB | view |
| 4k | 1,514 | 63.0 | 66.9 GB | view |
| 8k | 1,492 | 59.7 | 67.5 GB | view |
| 16k | 1,304 | 52.5 | 68.7 GB | view |
| 32k | 1,080 | 43.6 | 71.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.2 | 1.00× |
| 2× | 90.6 | 1.43× |
| 4× | 107.1 | 1.69× |