Eris GGUF models
70 GGUF models in the Eris family, quantized by 10 uploaders. Sizes run from 7.24B to 28.2B parameters. The longest trained context is 1000K tokens.
About the Eris GGUF models
Eris is represented on ggufmodels.com by 70 GGUF models, quantized by 10 uploaders on Hugging Face. The most downloaded are Eris PrimeV3 Vision 7B GGUF IQ Imatrix, Eris Daturamix 7b v2 GGUF IQ Imatrix and Eris PrimeV4.69 Vision 32k 7B GGUF Imatrix. Parameter counts run from 7.24B to 28.2B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Eris model is between 4.4 to 7.5 GB, which is the quant most people start with. Most files come from mradermacher (37), Lewdiculous (19) and weezywitasneezy (3). The quants you will meet most often are Q4_K_M (60), Q5_K_M (58), Q6_K (57) and Q5_K_S (56), where the number is how many models offer that quant.
Frequently asked questions
Which Eris GGUF should I download?
The most downloaded Eris GGUF here is Eris PrimeV3 Vision 7B GGUF IQ Imatrix. 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 Eris model need?
Q4_K_M files of Eris models on this site range from 4.4 to 7.5 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 Eris GGUF files come from?
The most common quantizers here are mradermacher, Lewdiculous and weezywitasneezy. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.