GGUF models by NexesQuants
283 GGUF models quantized by NexesQuants on Hugging Face. Sizes run from 488M to 141B parameters. The longest trained context is 256K tokens.
About NexesQuants on Hugging Face
NexesQuants has published 283 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Thedrummer. The most downloaded are WinterGoddess 1.4x limarpv3 70B L2 32k Requant, Dolphin3.0 Llama3.1 1B abliterated and senku-70b.
The quants NexesQuants publishes most often are Q8_0 (222), Q5_0 (191), BF16 (56) and Q3_K_M (13). Their Q4_K_M files range from 19.6 to 19.6 GB. Parameter counts run from 488M to 141B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has NexesQuants published?
283 models are listed here, mainly from the Llama, Gemma and Thedrummer families. The most downloaded is WinterGoddess 1.4x limarpv3 70B L2 32k Requant.
Which quants does NexesQuants publish?
The most common are Q8_0 (222 models), Q5_0 (191 models), BF16 (56 models) and Q3_K_M (13 models).