← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
836.3
PP tok/s
40.0
TG tok/s
1225
TTFT (ms)
123.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 836.3 | 40.0 | 123.3 GB | current |
| 4k | 950.5 | 38.7 | 124.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.0 | 1.00× |
| 2× | 64.0 | 1.60× |
| 4× | 92.7 | 2.32× |