← Back to community benchmarks
Qwen3.5-122B-A10B-oQ4
Performance
16k
tokens
925.0
PP tok/s
14.0
TG tok/s
17713
TTFT (ms)
75.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.22
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 800.4 | 15.1 | 69.2 GB | view |
| 4k | 1,052 | 15.0 | 72.1 GB | view |
| 8k | 1,046 | 14.5 | 73.3 GB | view |
| 16k | 925.0 | 14.0 | 75.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.1 | 1.00× |
| 2× | 27.2 | 1.80× |
| 4× | 47.0 | 3.11× |