Modelpublic

RichardErkhov/amd_-_Meta-Llama-3-8B_fp8_quark-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes691downloads

Model Card

Quantization made by Richard Erkhov.

Meta-Llama-3-8Bfp8quark - GGUF

Name	Quant method	Size
Meta-Llama-3-8B_fp8_quark.Q2_K.gguf	Q2_K	2.96GB
Meta-Llama-3-8B_fp8_quark.IQ3_XS.gguf	IQ3_XS	3.28GB
Meta-Llama-3-8B_fp8_quark.IQ3_S.gguf	IQ3_S	3.43GB
Meta-Llama-3-8B_fp8_quark.Q3_K_S.gguf	Q3KS	3.41GB
Meta-Llama-3-8B_fp8_quark.IQ3_M.gguf	IQ3_M	3.52GB
Meta-Llama-3-8B_fp8_quark.Q3_K.gguf	Q3_K	3.74GB
Meta-Llama-3-8B_fp8_quark.Q3_K_M.gguf	Q3KM	3.74GB
Meta-Llama-3-8B_fp8_quark.Q3_K_L.gguf	Q3KL	4.03GB
Meta-Llama-3-8B_fp8_quark.IQ4_XS.gguf	IQ4_XS	4.18GB
Meta-Llama-3-8B_fp8_quark.Q4_0.gguf	Q4_0	4.34GB
Meta-Llama-3-8B_fp8_quark.IQ4_NL.gguf	IQ4_NL	4.38GB
Meta-Llama-3-8B_fp8_quark.Q4_K_S.gguf	Q4KS	4.37GB
Meta-Llama-3-8B_fp8_quark.Q4_K.gguf	Q4_K	4.58GB
Meta-Llama-3-8B_fp8_quark.Q4_K_M.gguf	Q4KM	4.58GB
Meta-Llama-3-8B_fp8_quark.Q4_1.gguf	Q4_1	4.78GB
Meta-Llama-3-8B_fp8_quark.Q5_0.gguf	Q5_0	5.21GB
Meta-Llama-3-8B_fp8_quark.Q5_K_S.gguf	Q5KS	5.21GB
Meta-Llama-3-8B_fp8_quark.Q5_K.gguf	Q5_K	5.34GB
Meta-Llama-3-8B_fp8_quark.Q5_K_M.gguf	Q5KM	5.34GB
Meta-Llama-3-8B_fp8_quark.Q5_1.gguf	Q5_1	5.65GB
Meta-Llama-3-8B_fp8_quark.Q6_K.gguf	Q6_K	6.14GB
Meta-Llama-3-8B_fp8_quark.Q8_0.gguf	Q8_0	7.95GB

Original model description: Entry not found