← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
32k
tokens
344.5
PP tok/s
23.0
TG tok/s
95112
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.2.22
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 377.4 | 28.1 | 65.3 GB | view |
| 32k | 344.5 | 23.0 | 67.7 GB | current |