Ternary GGUF models
119 GGUF models in the Ternary family, quantized by 73 uploaders. Sizes run from 2M to 28.9B parameters. The longest trained context is 256K tokens.
About the Ternary GGUF models
Ternary is represented on ggufmodels.com by 119 GGUF models, quantized by 73 uploaders on Hugging Face. The most downloaded are Ternary Bonsai 8B, Ternary Bonsai 2 27B Uncensored Heretic and Ternary Bonsai 2 27B Uncensored Heretic v2. Parameter counts run from 2M to 28.9B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Ternary model is between 1.1 to 16.5 GB, which is the quant most people start with. Most files come from jinreiyu (6), ChezRD (4) and BoldingBuilds (4). The quants you will meet most often are Q2_0 (26), F16 (20), Q4_K_M (15) and Q2_K (12), where the number is how many models offer that quant.
Frequently asked questions
Which Ternary GGUF should I download?
The most downloaded Ternary GGUF here is Ternary Bonsai 8B. 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 Ternary model need?
Q4_K_M files of Ternary models on this site range from 1.1 to 16.5 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 Ternary GGUF files come from?
The most common quantizers here are jinreiyu, ChezRD and BoldingBuilds. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.