← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
4k
tokens
500.7
PP tok/s
44.8
TG tok/s
8180
TTFT (ms)
63.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 440.1 | 46.7 | 62.1 GB | view |
| 4k | 500.7 | 44.8 | 63.4 GB | current |
| 8k | 492.0 | 43.3 | 64.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.7 | 1.00× |
| 2× | 70.0 | 1.50× |
| 4× | 95.3 | 2.04× |