← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK-X
Performance
8k
tokens
421.7
PP tok/s
39.6
TG tok/s
19428
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 445.8 | 45.9 | 65.6 GB | view |
| 4k | 481.2 | 42.0 | 67.0 GB | view |
| 8k | 421.7 | 39.6 | 67.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.9 | 1.00× |
| 2× | 62.2 | 1.36× |
| 4× | 83.9 | 1.83× |