← Back to community benchmarks
Qwen3.5-VL-122B-A10B-6bitCRACK-X
Performance
4k
tokens
574.3
PP tok/s
36.8
TG tok/s
7133
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.22
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 517.1 | 38.2 | 94.9 GB | view |
| 4k | 574.3 | 36.8 | 96.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.2 | 1.00× |
| 2× | 55.9 | 1.46× |
| 4× | 68.3 | 1.79× |