← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK-X
Performance
1k
tokens
469.5
PP tok/s
52.7
TG tok/s
2181
TTFT (ms)
66.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 469.5 | 52.7 | 66.0 GB | current |
| 4k | 522.6 | 48.8 | 67.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.7 | 1.00× |
| 2× | 81.3 | 1.54× |
| 4× | 104.8 | 1.99× |
| 8× | 130.9 | 2.48× |