GGUF models by jsfs11
49 GGUF models quantized by jsfs11 on Hugging Face. Sizes run from 6.29B to 32.8B parameters. The longest trained context is 1000K tokens.
About jsfs11 on Hugging Face
jsfs11 has published 49 GGUF models that ggufmodels.com tracks, across families such as Stheno, Mixtureofmerges and Randommergenonormweighted. The most downloaded are WestOrcaNeuralMarco DPO v2 DARETIES 7B, MixtureofMerges MoE 2x7b v7 and TemptressTensor 10.7B v0.1a.
The quants jsfs11 publishes most often are Q5_K_M (24), Q8_0 (18), Q4_K_M (10) and Q6_K (5). Their Q4_K_M files range from 7.8 to 19.8 GB. Parameter counts run from 6.29B to 32.8B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has jsfs11 published?
49 models are listed here, mainly from the Stheno, Mixtureofmerges and Randommergenonormweighted families. The most downloaded is WestOrcaNeuralMarco DPO v2 DARETIES 7B.
Which quants does jsfs11 publish?
The most common are Q5_K_M (24 models), Q8_0 (18 models), Q4_K_M (10 models) and Q6_K (5 models).