← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
1,085
PP tok/s
33.8
TG tok/s
15098
TTFT (ms)
95.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 975.0 | 52.5 | 94.0 GB | view |
| 4k | 1,253 | 50.4 | 94.2 GB | view |
| 8k | 1,228 | 48.6 | 94.6 GB | view |
| 16k | 1,085 | 33.8 | 95.3 GB | current |
| 32k | 888.3 | 27.7 | 96.7 GB | view |
| 64k | 696.4 | 21.9 | 99.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.5 | 1.00× |
| 2× | 64.3 | 1.22× |
| 4× | 75.7 | 1.44× |
| 8× | 88.6 | 1.69× |