← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK-X
Performance
1k
tokens
445.3
PP tok/s
46.3
TG tok/s
2299
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 445.3 | 46.3 | 65.6 GB | current |
| 4k | 487.9 | 42.5 | 67.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.3 | 1.00× |
| 2× | 62.4 | 1.35× |
| 4× | 69.9 | 1.51× |