inference-net/Schematron-3B download history
inference-net/Schematron-3B is a 3.2B-parameter text generation model by inference-net. In the last 30 days it was downloaded 668 times (99 in the last 7 days), and 3,480,821 times in total.
It ranks #56,767 on the Hub by monthly downloads and #13,571 among text generation models.
It has 343 likes.
It is a fine-tune of meta-llama/Llama-3.2-3B-Instruct.
12 models build on Schematron-3B: 9 quantized, 3 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 2,450 times in the last 30 days. See the Schematron-3B galaxy.
Most downloaded derivatives
- mradermacher/Schematron-3B-i1-GGUF (quantized), 811 downloads in 30 days
- mradermacher/Schematron-3B-GGUF (quantized), 436 downloads in 30 days
- DevQuasar/inference-net.Schematron-3B-GGUF (quantized), 177 downloads in 30 days
- MaziyarPanahi/Schematron-3B-GGUF (quantized), 128 downloads in 30 days
- Open4bits/Schematron-3B-gguf (quantized), 98 downloads in 30 days
- pchamart/schematron3B-mlx-8bit (quantized), 38 downloads in 30 days
- debaasvan/Schematron-3B-Q4_K_M-GGUF (quantized), 37 downloads in 30 days
- Otilde/Schematron-3B-mxfp4-F32-MLX (finetune), 22 downloads in 30 days
- onnx-community/Schematron-3B-ONNX (quantized), 12 downloads in 30 days
- manu02/Schematron-3B-bnb-4bit-nf4-dq (quantized), 11 downloads in 30 days
- PrunaAI/inference-net-Schematron-3B-HQQ-8bit-smashed (finetune), 9 downloads in 30 days
- PrunaAI/inference-net-Schematron-3B-HQQ-4bit-smashed (finetune), 3 downloads in 30 days