← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK-X
Performance
1k
tokens
522.3
PP tok/s
57.8
TG tok/s
1961
TTFT (ms)
67.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.3
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 522.3 | 57.8 | 67.5 GB | current |
| 4k | 589.6 | 55.8 | 68.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.8 | 1.00× |
| 2× | 89.2 | 1.54× |
| 4× | 112.7 | 1.95× |