← Back to community benchmarks
Qwen3.5-122B-A10B-RAM-48GB
Performance
16k
tokens
162.3
PP tok/s
24.4
TG tok/s
100971
TTFT (ms)
47.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 177.5 | 28.4 | 44.8 GB | view |
| 16k | 162.3 | 24.4 | 47.5 GB | current |
| 64k | 104.1 | 18.3 | 49.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.4 | 1.00× |
| 2× | 30.9 | 1.09× |
| 4× | 61.8 | 2.18× |