XortronCriminalComputingConfig
by darkc0de
23.6B params · text-generation · 133 likes · 649 downloads
XortronCriminalComputingConfig is a 23.6B parameter model. At Q4 quantization it requires 12GB of VRAM. It runs comfortably on GeForce RTX 4090 (55 tok/s), GeForce RTX 5090 (83 tok/s), A100 PCIe 80 GB (102 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 55 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 83 tok/s | comfortable |
| M4 Max 128GB | 128GB | 20 tok/s | tight |
| M4 Pro 48GB | 48GB | 10 tok/s | tight |
| M4 Pro 24GB | 24GB | 10 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 102 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 205 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 49 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 40 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 39 tok/s | comfortable |