Create README.md

README.md

@@ -0,0 +1,29 @@
+---
+license: mit
+base_model: z-lab/gemma-4-31B-it-DFlash
+base_model_relation: quantized
+quantized_by: turboderp
+tags:
+- exl3
+---
+
+EXL3 quants of [gemma-4-31B-it-DFlash](https://huggingface.co/z-lab/gemma-4-31B-it-DFlash)
+
+[2.50 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/2.50bpw)    
+[3.00 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/3.00bpw)    
+[3.50 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/3.50bpw)    
+[4.00 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/4.00bpw)    
+[5.00 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/5.00bpw)    
+[6.00 bits per weight](https://huggingface.co/turboderp/gemma4-31b-it-DFlash-exl3/tree/6.00bpw)    
+
+Quant    | Mean acc. tokens¹
+---------|------------------
+2.50 bpw | 4.00
+3.00 bpw | 4.07
+3.50 bpw | 4.08
+4.00 bpw | 4.10
+5.00 bpw | 4.12
+6.00 bpw | 4.10
+BF16     | 4.07
+
+¹ Mean verified tokens per 15-token draft, CatBench at temp=0, using 4.00bpw target model on current exllamav3 `dev` branch (upcoming v0.0.33)