GGUF models by elliotthwang
43 GGUF models quantized by elliotthwang on Hugging Face. Sizes run from 12M to 8.03B parameters. The longest trained context is 128K tokens.
About elliotthwang on Hugging Face
elliotthwang has published 43 GGUF models that ggufmodels.com tracks, across families such as Llama, Phi and Mistral. The most downloaded are KimLan zh LLaMa GPTQ, KimLan zh LLaMa GPTQ V1.0 and KimLan gemma2.
The quants elliotthwang publishes most often are Q4_K_M (11), Q8_0 (9), Q5_K_M (9) and F16 (2). Their Q4_K_M files range from 1.7 to 4.9 GB. Parameter counts run from 12M to 8.03B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has elliotthwang published?
43 models are listed here, mainly from the Llama, Phi and Mistral families. The most downloaded is KimLan zh LLaMa GPTQ.
Which quants does elliotthwang publish?
The most common are Q4_K_M (11 models), Q8_0 (9 models), Q5_K_M (9 models) and F16 (2 models).