GGUF models by ArtusDev
38 GGUF models quantized by ArtusDev on Hugging Face. Sizes run from 3.88B to 671B parameters. The longest trained context is 256K tokens.
About ArtusDev on Hugging Face
ArtusDev has published 38 GGUF models that ggufmodels.com tracks, across families such as Gemma, Toastypigeon and Glitterfetti. The most downloaded are Confetti, yvvki Erotophobia 24B v1.1 and Salesforce xgen small 9B instruct r.
The quants ArtusDev publishes most often are Q8_0 (36), Q6_K (32), Q5_K_M (30) and Q5_K_S (25). Their Q4_K_M files range from 2.5 to 42.5 GB. Parameter counts run from 3.88B to 671B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has ArtusDev published?
38 models are listed here, mainly from the Gemma, Toastypigeon and Glitterfetti families. The most downloaded is Confetti.
Which quants does ArtusDev publish?
The most common are Q8_0 (36 models), Q6_K (32 models), Q5_K_M (30 models) and Q5_K_S (25 models).