Vibethinker GGUF models
91 GGUF models in the Vibethinker family, quantized by 58 uploaders. Sizes run from 30M to 3.4B parameters. The longest trained context is 128K tokens.
About the Vibethinker GGUF models
Vibethinker is represented on ggufmodels.com by 91 GGUF models, quantized by 58 uploaders on Hugging Face. The most downloaded are VibeThinker 3B, Mythos Nano Final and VibeThinker 3B. Parameter counts run from 30M to 3.4B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Vibethinker model is between 1.0 to 2.1 GB, which is the quant most people start with. Most files come from mradermacher (20), sizzlebop (4) and prithivMLmods (3). The quants you will meet most often are Q4_K_M (63), Q8_0 (55), Q5_K_M (48) and Q6_K (47), where the number is how many models offer that quant.
Frequently asked questions
Which Vibethinker GGUF should I download?
The most downloaded Vibethinker GGUF here is VibeThinker 3B. 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 Vibethinker model need?
Q4_K_M files of Vibethinker models on this site range from 1.0 to 2.1 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 Vibethinker GGUF files come from?
The most common quantizers here are mradermacher, sizzlebop and prithivMLmods. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.