xlm-roberta-base-language-detection
by papluca
278M params · text-classification · 375 likes · 578.0k downloads
xlm-roberta-base-language-detection is a 278M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (4722 tok/s), GeForce RTX 5090 (7081 tok/s), M4 Max 128GB (1727 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| HF Inference |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 4722 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 7081 tok/s | comfortable |
| M4 Max 128GB | 128GB | 1727 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 863 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 863 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 8651 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 17400 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 4174 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 3452 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 3351 tok/s | comfortable |