← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
4k
tokens
471.0
PP tok/s
47.1
TG tok/s
8697
TTFT (ms)
62.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 417.0 | 49.3 | 62.0 GB | view |
| 4k | 471.0 | 47.1 | 62.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 76.0 | 1.54× |
| 4× | 99.7 | 2.02× |