← Back to community benchmarks
Qwen3.5-122B-A10B-LMQ6.5
Performance
64k
tokens
754.8
PP tok/s
35.1
TG tok/s
86822
TTFT (ms)
101.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.6
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,143 | 48.8 | 94.0 GB | view |
| 4k | 1,526 | 48.0 | 95.4 GB | view |
| 8k | 1,432 | 46.6 | 96.0 GB | view |
| 16k | 1,283 | 43.1 | 97.2 GB | view |
| 32k | 1,041 | 40.9 | 99.6 GB | view |
| 64k | 754.8 | 35.1 | 101.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.8 | 1.00× |
| 2× | 98.8 | 2.02× |
| 4× | 193.1 | 3.96× |
| 8× | 406.7 | 8.33× |