mdeberta-v3-base-squad2
by timpal0l
278M params · question-answering · 257 likes · 363.6k downloads
mdeberta-v3-base-squad2 is a 278M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (4719 tok/s), GeForce RTX 5090 (7077 tok/s), M4 Max 128GB (1726 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| HF Inference |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 4719 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 7077 tok/s | comfortable |
| M4 Max 128GB | 128GB | 1726 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 863 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 863 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 8646 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 17390 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 4172 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 3450 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 3349 tok/s | comfortable |