← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
1k
tokens
407.2
PP tok/s
48.5
TG tok/s
2515
TTFT (ms)
62.0
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 407.2 | 48.5 | 62.0 GB | current |
| 4k | 462.2 | 44.6 | 62.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.5 | 1.00× |
| 2× | 74.3 | 1.53× |
| 4× | 99.3 | 2.05× |