← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
4k
tokens
367.5
PP tok/s
35.3
TG tok/s
11147
TTFT (ms)
63.5
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
96 GB
GPU Cores
30
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 341.6 | 38.8 | 62.0 GB | view |
| 4k | 367.5 | 35.3 | 63.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.8 | 1.00× |
| 2× | 56.3 | 1.45× |
| 4× | 68.8 | 1.77× |