Meliodaspercival GGUF models
115 GGUF models in the Meliodaspercival family, quantized by 2 uploaders. Sizes run from 7.24B to 7.24B parameters. The longest trained context is 32K tokens.
About the Meliodaspercival GGUF models
Meliodaspercival is represented on ggufmodels.com by 115 GGUF models, quantized by 2 uploaders on Hugging Face. The most downloaded are MeliodasPercival_01_Experiment28Experiment26, Ognoexperiment27multi verse modelMeliodaspercival 01 experiment26t3q 7B and MeliodasPercival_01_Strangemerges_32Shadow. Parameter counts run from 7.24B to 7.24B, and the longest trained context window is 32K tokens.
A Q4_K_M file of a Meliodaspercival model is between 4.4 to 4.4 GB, which is the quant most people start with. Most files come from mradermacher (114) and MaziyarPanahi (1). The quants you will meet most often are Q8_0 (115), Q6_K (115), Q5_K_S (115) and Q5_K_M (115), where the number is how many models offer that quant.
Frequently asked questions
Which Meliodaspercival GGUF should I download?
The most downloaded Meliodaspercival GGUF here is MeliodasPercival_01_Experiment28Experiment26. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Meliodaspercival model need?
Q4_K_M files of Meliodaspercival models on this site range from 4.4 to 4.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Meliodaspercival GGUF files come from?
The most common quantizers here are mradermacher and MaziyarPanahi. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.