Bonsai-8B-gguf
by prism-ml
8.0B params · text-generation · 721 likes · 18.0k downloads
Bonsai-8B-gguf is a 8.0B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (164 tok/s), GeForce RTX 5090 (246 tok/s), M4 Max 128GB (60 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 164 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 246 tok/s | comfortable |
| M4 Max 128GB | 128GB | 60 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 30 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 30 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 300 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 604 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 145 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 120 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 116 tok/s | comfortable |