← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
64k
tokens
196.2
PP tok/s
1.4
TG tok/s
334012
TTFT (ms)
71.9
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
128 GB
GPU Cores
48
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 259.4 | 34.6 | 66.3 GB | view |
| 4k | 275.3 | 30.4 | 66.7 GB | view |
| 8k | 273.2 | 21.6 | 67.0 GB | view |
| 16k | 264.2 | 10.7 | 67.7 GB | view |
| 32k | 239.8 | 4.9 | 69.1 GB | view |
| 64k | 196.2 | 1.4 | 71.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.6 | 1.00× |
| 2× | 48.4 | 1.40× |
| 4× | 60.1 | 1.74× |