CoolFace
Modelpublic

Alcoft/dnotitia_Smoothie-Qwen3-0.6B-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes1.4kdownloads
Model Card
QuantSizeDescription
Q2_K_XXS209.49 MBNot recommended for most people. Extremelly low quality.
Q2_K_XS209.49 MBNot recommended for most people. Very low quality.
Q2_K209.49 MBNot recommended for most people. Very low quality.
Q2_K_L318.45 MBNot recommended for most people. Uses Q80 for output and embedding, and Q2K for everything else. Very low quality.
Q2_K_XL457.55 MBNot recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.
Q3_K_XXS250.15 MBNot recommended for most people. Prefer any bigger Q3_K quantization. Very low quality.
Q3_K_XS250.15 MBNot recommended for most people. Prefer any bigger Q3_K quantization. Very low quality.
Q3_K_S250.15 MBNot recommended for most people. Prefer any bigger Q3_K quantization. Low quality.
Q3_K_M273.09 MBNot recommended for most people. Low quality.
Q3_K_L293.46 MBNot recommended for most people. Low quality.
Q3_K_XL387.36 MBNot recommended for most people. Uses Q80 for output and embedding, and Q3K_L for everything else. Low quality.
Q3_K_XXL526.46 MBNot recommended for most people. Uses F16 for output and embedding, and Q3KL for everything else. Low quality.
Q4_K_XS327.26 MBLower quality than Q4KS.
Q4_K_S327.26 MBRecommended. Slightly low quality.
Q4_K_M340.07 MBRecommended. Decent quality for most use cases.
Q4_K_L414.26 MBRecommended. Uses Q80 for output and embedding, and Q4K_M for everything else. Decent quality.
Q4_K_XL553.36 MBRecommended. Uses F16 for output and embedding, and Q4KM for everything else. Decent quality.
Q5_K_XXS396.68 MBLower quality than Q5KS.
Q5_K_XS396.68 MBLower quality than Q5KS.
Q5_K_S396.68 MBRecommended. High quality.
Q5_K_M404.12 MBRecommended. High quality.
Q5_K_L459.76 MBRecommended. Uses Q80 for output and embedding, and Q5K_M for everything else. High quality.
Q5_K_XL598.86 MBRecommended. Uses F16 for output and embedding, and Q5KM for everything else. High quality.
Q6_K_S472.17 MBLower quality than Q6_K.
Q6_K472.17 MBRecommended. Very high quality.
Q6_K_L508.11 MBRecommended. Uses Q80 for output and embedding, and Q6K for everything else. Very high quality.
Q6_K_XL647.21 MBRecommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.
Q8_K_XS609.82 MBLower quality than Q8_0.
Q8_K_S609.82 MBLower quality than Q8_0.
Q8_0609.82 MBRecommended. Quality almost like F16.
Q8_K_XL748.93 MBRecommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.
F161.12 GBNot recommended. Overkill. Prefer Q8_0.
ORIGINAL (BF16)1.12 GBNot recommended. Overkill. Prefer Q8_0.

Quantized using TAO71-AI AutoQuantizer. You can check out the original model card here.