37 lines
4.5 KiB
Markdown
37 lines
4.5 KiB
Markdown
---
|
|
base_model:
|
|
- Qwen/Qwen3-0.6B
|
|
pipeline_tag: text-generation
|
|
license: apache-2.0
|
|
---
|
|
|
|
|Quant|Size|Description|
|
|
|---|---|---|
|
|
|[Q2_K](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K.gguf)|331.2 MB|Not recommended for most people. Very low quality.|
|
|
|[Q2_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K_L.gguf)|476.1 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/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K_XL.gguf)|754.3 MB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.|
|
|
|[Q3_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_S.gguf)|371.86 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.|
|
|
|[Q3_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_M.gguf)|394.8 MB|Not recommended for most people. Low quality.|
|
|
|[Q3_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_L.gguf)|415.18 MB|Not recommended for most people. Low quality.|
|
|
|[Q3_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_XL.gguf)|545.0 MB|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/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_XXL.gguf)|823.21 MB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.|
|
|
|[Q4_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_S.gguf)|448.98 MB|Recommended. Slightly low quality.|
|
|
|[Q4_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_M.gguf)|461.79 MB|Recommended. Decent quality for most use cases.|
|
|
|[Q4_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_L.gguf)|571.91 MB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.|
|
|
|[Q4_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_XL.gguf)|850.11 MB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.|
|
|
|[Q5_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_S.gguf)|518.4 MB|Recommended. High quality.|
|
|
|[Q5_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_M.gguf)|525.84 MB|Recommended. High quality.|
|
|
|[Q5_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_L.gguf)|617.41 MB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.|
|
|
|[Q5_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_XL.gguf)|895.61 MB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.|
|
|
|[Q6_K](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K.gguf)|593.88 MB|Recommended. Very high quality.|
|
|
|[Q6_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K_L.gguf)|665.75 MB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.|
|
|
|[Q6_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K_XL.gguf)|943.96 MB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.|
|
|
|[Q8_0](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q8_0.gguf)|767.47 MB|Recommended. Quality almost like F16.|
|
|
|[Q8_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q8_K_XL.gguf)|1.02 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.|
|
|
|[F16](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_F16.gguf)|1.41 GB|Not recommended. Overkill. Prefer Q8_0.|
|
|
|[ORIGINAL (BF16)](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B.gguf)|1.41 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/Qwen/Qwen3-0.6B). |