← Back to community benchmarks
Qwen3.5-122B-A10B6.5bit
Performance
1k
tokens
718.8
PP tok/s
49.4
TG tok/s
1425
TTFT (ms)
94.0
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
256 GB
GPU Cores
80
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 718.8 | 49.4 | 94.0 GB | current |
| 4k | 903.1 | 47.6 | 95.5 GB | view |
| 8k | 913.5 | 45.2 | 96.1 GB | view |
| 16k | 864.1 | 41.0 | 97.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.4 | 1.00× |
| 2× | 78.7 | 1.59× |
| 4× | 105.2 | 2.13× |
| 8× | 137.6 | 2.79× |