← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
16k
tokens
1,151
PP tok/s
52.1
TG tok/s
14241
TTFT (ms)
65.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,045 | 61.5 | 62.0 GB | view |
| 4k | 1,449 | 61.8 | 63.4 GB | view |
| 8k | 1,319 | 58.3 | 64.0 GB | view |
| 16k | 1,151 | 52.1 | 65.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.5 | 1.00× |
| 2× | 94.9 | 1.54× |
| 4× | 118.2 | 1.92× |