GGUF models by Aryanne
54 GGUF models quantized by Aryanne on Hugging Face. Sizes run from 1.1B to 32.8B parameters. The longest trained context is 128K tokens.
About Aryanne on Hugging Face
Aryanne has published 54 GGUF models that ggufmodels.com tracks, across families such as Llama, Tinyllama and Sheared. The most downloaded are Open StarLake Swap 7B, MedWest 7B and Mamba gpt 3B v4 ggml and.
The quants Aryanne publishes most often are Q4_0 (32), F16 (17), Q5_0 (16) and Q4_1 (15). Their Q4_K_M files range from 1.6 to 4.4 GB. Parameter counts run from 1.1B to 32.8B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has Aryanne published?
54 models are listed here, mainly from the Llama, Tinyllama and Sheared families. The most downloaded is Open StarLake Swap 7B.
Which quants does Aryanne publish?
The most common are Q4_0 (32 models), F16 (17 models), Q5_0 (16 models) and Q4_1 (15 models).