← Back to community benchmarks
Qwen3.5-VL-122B-A10B-4bitCRACK
Performance
1k
tokens
512.6
PP tok/s
55.6
TG tok/s
1998
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 512.6 | 55.6 | 65.6 GB | current |
| 4k | 579.4 | 52.0 | 67.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.6 | 1.00× |
| 2× | 90.3 | 1.62× |
| 4× | 112.8 | 2.03× |