← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
417.0
PP tok/s
33.1
TG tok/s
39287
TTFT (ms)
69.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 487.5 | 44.1 | 66.4 GB | view |
| 4k | 514.6 | 42.2 | 67.9 GB | view |
| 8k | 473.6 | 39.1 | 68.5 GB | view |
| 16k | 417.0 | 33.1 | 69.7 GB | current |
| 32k | 319.9 | 16.3 | 72.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.1 | 1.00× |
| 2× | 31.1 | 0.71× |
| 4× | 47.7 | 1.08× |