← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
4k
tokens
378.1
PP tok/s
43.4
TG tok/s
10832
TTFT (ms)
62.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
128 GB
GPU Cores
60
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 340.6 | 45.8 | 62.0 GB | view |
| 4k | 378.1 | 43.4 | 62.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.8 | 1.00× |
| 2× | 66.0 | 1.44× |
| 4× | 81.1 | 1.77× |