Qwopus GGUF models
187 GGUF models in the Qwopus family, quantized by 86 uploaders. Sizes run from 1M to 35.5B parameters. The longest trained context is 256K tokens.
About the Qwopus GGUF models
Qwopus is represented on ggufmodels.com by 187 GGUF models, quantized by 86 uploaders on Hugging Face. The most downloaded are Qwopus3.8 27B Flash V2, Qwopus3.6 35B A3B Coder and Qwopus3.6 27B v2. Parameter counts run from 1M to 35.5B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Qwopus model is between 0.5 to 21.7 GB, which is the quant most people start with. Most files come from mradermacher (51), Jackrong (11) and zaydiscold (9). The quants you will meet most often are Q4_K_M (110), Q5_K_M (92), Q6_K (89) and Q8_0 (77), where the number is how many models offer that quant.
Frequently asked questions
Which Qwopus GGUF should I download?
The most downloaded Qwopus GGUF here is Qwopus3.8 27B Flash V2. 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 Qwopus model need?
Q4_K_M files of Qwopus models on this site range from 0.5 to 21.7 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 Qwopus GGUF files come from?
The most common quantizers here are mradermacher, Jackrong and zaydiscold. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.