Hugging Peers

BeaverAI_-_NeMoist-21B-v1a-gguf

☆ Save
by RichardErkhov
42.3K downloads 0 likes on Hugging Face updated

Model card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NeMoist-21B-v1a - GGUF

  • Model creator: https://huggingface.co/BeaverAI/
  • Original model: https://huggingface.co/BeaverAI/NeMoist-21B-v1a/
Name Quant method Size
NeMoist-21B-v1a.Q2_K.gguf Q2_K 7.26GB
NeMoist-21B-v1a.IQ3_XS.gguf IQ3_XS 8.05GB
NeMoist-21B-v1a.IQ3_S.gguf IQ3_S 4.72GB
NeMoist-21B-v1a.Q3_K_S.gguf Q3_K_S 5.76GB
NeMoist-21B-v1a.IQ3_M.gguf IQ3_M 0.34GB
NeMoist-21B-v1a.Q3_K.gguf Q3_K 0.11GB
NeMoist-21B-v1a.Q3_K_M.gguf Q3_K_M 0.02GB
NeMoist-21B-v1a.Q3_K_L.gguf Q3_K_L 0.0GB
NeMoist-21B-v1a.IQ4_XS.gguf IQ4_XS 0.0GB
NeMoist-21B-v1a.Q4_0.gguf Q4_0 0.0GB
NeMoist-21B-v1a.IQ4_NL.gguf IQ4_NL 0.0GB
NeMoist-21B-v1a.Q4_K_S.gguf Q4_K_S 0.0GB
NeMoist-21B-v1a.Q4_K.gguf Q4_K 0.0GB
NeMoist-21B-v1a.Q4_K_M.gguf Q4_K_M 0.0GB
NeMoist-21B-v1a.Q4_1.gguf Q4_1 0.0GB
NeMoist-21B-v1a.Q5_0.gguf Q5_0 0.0GB
NeMoist-21B-v1a.Q5_K_S.gguf Q5_K_S 0.0GB
NeMoist-21B-v1a.Q5_K.gguf Q5_K 0.0GB
NeMoist-21B-v1a.Q5_K_M.gguf Q5_K_M 0.0GB
NeMoist-21B-v1a.Q5_1.gguf Q5_1 0.0GB
NeMoist-21B-v1a.Q6_K.gguf Q6_K 0.0GB
NeMoist-21B-v1a.Q8_0.gguf Q8_0 0.0GB

Original model description: Entry not found