← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
32k
tokens
443.9
PP tok/s
29.0
TG tok/s
73826
TTFT (ms)
64.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 503.9 | 57.1 | 62.0 GB | view |
| 4k | 553.4 | 53.9 | 62.3 GB | view |
| 8k | 537.1 | 48.4 | 62.6 GB | view |
| 16k | 482.7 | 40.0 | 63.3 GB | view |
| 32k | 443.9 | 29.0 | 64.7 GB | current |
| 64k | 353.6 | 18.9 | 67.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.1 | 1.00× |
| 2× | 86.4 | 1.51× |
| 4× | 118.8 | 2.08× |