← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK-X
Performance
16k
tokens
2,104
PP tok/s
53.7
TG tok/s
7789
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 566.7 | 55.2 | 66.8 GB | view |
| 4k | 600.8 | 52.8 | 68.3 GB | view |
| 8k | 587.2 | 50.3 | 68.9 GB | view |
| 16k | 2,104 | 53.7 | 67.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.2 | 1.00× |
| 2× | 84.1 | 1.52× |
| 4× | 108.2 | 1.96× |