GGUF models by v000000
34 GGUF models quantized by v000000 on Hugging Face. Sizes run from 7.24B to 46.7B parameters. The longest trained context is 1000K tokens.
About v000000 on Hugging Face
v000000 has published 34 GGUF models that ggufmodels.com tracks, across families such as Mysticgem, Niitorm and Tripletboreas. The most downloaded are L3.1 Niitorm 8B LATCOSx2 Version GGUFs IMATRIX, L3.1 Niitorm 8B DPO t0.0001 GGUFs IMATRIX and Llama 3.1 8B Stheno v3.4.
The quants v000000 publishes most often are Q6_K (14), Q8_0 (13), Q5_K_M (8) and Q5_K_S (4). Their Q4_K_M files range from 4.9 to 12.0 GB. Parameter counts run from 7.24B to 46.7B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has v000000 published?
34 models are listed here, mainly from the Mysticgem, Niitorm and Tripletboreas families. The most downloaded is L3.1 Niitorm 8B LATCOSx2 Version GGUFs IMATRIX.
Which quants does v000000 publish?
The most common are Q6_K (14 models), Q8_0 (13 models), Q5_K_M (8 models) and Q5_K_S (4 models).