Update README.md

README.md

@@ -11,4 +11,22 @@ tags:
 - medical
 ---
 
-> II-Medical-8B is an advanced 8-billion parameter medical large language model developed by Intelligent Internet, fine-tuned from Qwen3-8B to deliver exceptional performance in AI-driven medical reasoning and question-answering through extensive supervised and reinforcement learning on diverse public and synthetic healthcare datasets. Leveraging a precision-crafted four-stage training pipeline—including thorough data curation, decontamination, and enrichment with over 555,000 curated samples—the model excels at step-by-step clinical reasoning, robust evaluation on ten major medical QA benchmarks, achieving an average score competitive with top models like GPT-4.5 and HuatuoGPT-o1. Designed for compatibility with frameworks such as vLLM and SGLang, II-Medical-8B provides comprehensive, transparent medical reasoning responses but is not intended for real clinical use, with recommended sampling and output formatting guidelines to ensure clarity and safety in research and experimental settings
+# **II-Medical-8B-f32-GGUF**
+
+> II-Medical-8B is an advanced 8-billion parameter medical large language model developed by Intelligent Internet, fine-tuned from Qwen3-8B to deliver exceptional performance in AI-driven medical reasoning and question-answering through extensive supervised and reinforcement learning on diverse public and synthetic healthcare datasets. Leveraging a precision-crafted four-stage training pipeline—including thorough data curation, decontamination, and enrichment with over 555,000 curated samples—the model excels at step-by-step clinical reasoning, robust evaluation on ten major medical QA benchmarks, achieving an average score competitive with top models like GPT-4.5 and HuatuoGPT-o1. Designed for compatibility with frameworks such as vLLM and SGLang, II-Medical-8B provides comprehensive, transparent medical reasoning responses but is not intended for real clinical use, with recommended sampling and output formatting guidelines to ensure clarity and safety in research and experimental settings.
+
+## Model Files
+
+| File Name | Quant Type | File Size |
+| - | - | - |
+| II-Medical-8B.F16.gguf | F16 | 16.4 GB |
+| II-Medical-8B.F32.gguf | F32 | 32.8 GB |
+
+## Quants Usage 
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)