← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
1k
tokens
503.2
PP tok/s
58.4
TG tok/s
2035
TTFT (ms)
62.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 503.2 | 58.4 | 62.0 GB | current |
| 4k | 556.4 | 55.0 | 62.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.4 | 1.00× |
| 2× | 90.0 | 1.54× |
| 4× | 115.6 | 1.98× |