初始化项目，由ModelHub XC社区提供模型

Model: Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF Source: Original Platform
2026-10-26 18:26:17 +08:00
commit 800860913f
35 changed files with 223 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,56 @@
+---
+base_model:
+- dnotitia/Smoothie-Qwen3-1.7B
+pipeline_tag: text-generation
+language:
+- en
+license: apache-2.0
+tags:
+- dnotitia
+- nlp
+- llm
+- conversation
+- chat
+- reasoning
+---
+
+|Quant|Size|Description|
+|---|---|---|
+|[Q2_K_XXS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q2_K_XXS.gguf)|595.71 MB|Not recommended for most people. Extremelly low quality.|
+|[Q2_K_XS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q2_K_XS.gguf)|595.71 MB|Not recommended for most people. Very low quality.|
+|[Q2_K](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q2_K.gguf)|595.71 MB|Not recommended for most people. Very low quality.|
+|[Q2_K_L](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q2_K_L.gguf)|813.63 MB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.|
+|[Q2_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q2_K_XL.gguf)|1.07 GB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.|
+|[Q3_K_XXS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_XXS.gguf)|711.16 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Very low quality.|
+|[Q3_K_XS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_XS.gguf)|711.16 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Very low quality.|
+|[Q3_K_S](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_S.gguf)|711.16 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.|
+|[Q3_K_M](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_M.gguf)|780.1 MB|Not recommended for most people. Low quality.|
+|[Q3_K_L](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_L.gguf)|841.1 MB|Not recommended for most people. Low quality.|
+|[Q3_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_XL.gguf)|1.0 GB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.|
+|[Q3_K_XXL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q3_K_XXL.gguf)|1.28 GB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.|
+|[Q4_K_XS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q4_K_XS.gguf)|934.57 MB|Lower quality than Q4_K_S.|
+|[Q4_K_S](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q4_K_S.gguf)|934.57 MB|Recommended. Slightly low quality.|
+|[Q4_K_M](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q4_K_M.gguf)|979.6 MB|Recommended. Decent quality for most use cases.|
+|[Q4_K_L](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q4_K_L.gguf)|1.1 GB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.|
+|[Q4_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q4_K_XL.gguf)|1.37 GB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.|
+|[Q5_K_XXS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_XXS.gguf)|1.11 GB|Lower quality than Q5_K_S.|
+|[Q5_K_XS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_XS.gguf)|1.11 GB|Lower quality than Q5_K_S.|
+|[Q5_K_S](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_S.gguf)|1.11 GB|Recommended. High quality.|
+|[Q5_K_M](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_M.gguf)|1.13 GB|Recommended. High quality.|
+|[Q5_K_L](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_L.gguf)|1.24 GB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.|
+|[Q5_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q5_K_XL.gguf)|1.51 GB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.|
+|[Q6_K_S](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q6_K_S.gguf)|1.32 GB|Lower quality than Q6_K.|
+|[Q6_K](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q6_K.gguf)|1.32 GB|Recommended. Very high quality.|
+|[Q6_K_L](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q6_K_L.gguf)|1.39 GB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.|
+|[Q6_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q6_K_XL.gguf)|1.66 GB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.|
+|[Q8_K_XS](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q8_K_XS.gguf)|1.71 GB|Lower quality than Q8_0.|
+|[Q8_K_S](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q8_K_S.gguf)|1.71 GB|Lower quality than Q8_0.|
+|[Q8_0](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q8_0.gguf)|1.71 GB|Recommended. Quality almost like F16.|
+|[Q8_K_XL](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_Q8_K_XL.gguf)|1.98 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.|
+|[F16](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B_F16.gguf)|3.21 GB|Not recommended. Overkill. Prefer Q8_0.|
+|[ORIGINAL (BF16)](https://huggingface.co/Alcoft/dnotitia_Smoothie-Qwen3-1.7B-GGUF/resolve/main/dnotitia_Smoothie-Qwen3-1.7B.gguf)|3.21 GB|Not recommended. Overkill. Prefer Q8_0.|
+
+---
+
+Quantized using [TAO71-AI AutoQuantizer](https://github.com/TAO71-AI/AutoQuantizer).
+You can check out the original model card [here](https://huggingface.co/dnotitia/Smoothie-Qwen3-1.7B).