GGUF models by vultr
35 GGUF models quantized by vultr on Hugging Face. Sizes run from 3.66B to 743B parameters. The longest trained context is 1024K tokens.
About vultr on Hugging Face
vultr has published 35 GGUF models that ggufmodels.com tracks, across families such as Nemotron, Qwen and Ling. The most downloaded are MiMo-V2.6-Flash-RL, NVIDIA-Nemotron-3-Nano-30B-A3B and Nex-N2.5-mini.
The quants vultr publishes most often are IQ3_S (35), IQ3_M (35), Q5_K_M (31) and Q4_K_M (31). Their Q4_K_M files range from 2.5 to 492.8 GB. Parameter counts run from 3.66B to 743B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has vultr published?
35 models are listed here, mainly from the Nemotron, Qwen and Ling families. The most downloaded is MiMo-V2.6-Flash-RL.
Which quants does vultr publish?
The most common are IQ3_S (35 models), IQ3_M (35 models), Q5_K_M (31 models) and Q4_K_M (31 models).