← Back to community benchmarks
Qwen3.5-122B-A10B-oQ4
Performance
16k
tokens
1,407
PP tok/s
11.3
TG tok/s
11644
TTFT (ms)
71.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 439.0 | 40.0 | 67.7 GB | view |
| 16k | 1,407 | 11.3 | 71.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.0 | 1.00× |
| 2× | 58.8 | 1.47× |
| 4× | 67.6 | 1.69× |