Qwen GGUF models
37395 GGUF models in the Qwen family, quantized by 10101 uploaders. Sizes run from 1M to 2450B parameters. The longest trained context is 3906K tokens.
About the Qwen GGUF models
Qwen is represented on ggufmodels.com by 37,395 GGUF models, quantized by 10,101 uploaders on Hugging Face. The most downloaded are Qwen3.8 Flash Next GSQ RCO, Qwen3.8-27B and Qwen3.8-27B iMatrix NVFP4 MTP. Parameter counts run from 1M to 2450B, and the longest trained context window is 3906K tokens.
A Q4_K_M file of a Qwen model is between 0.0 to 1481.4 GB, which is the quant most people start with. Most files come from mradermacher (10541), Thireus (1794) and RichardErkhov (1159). The quants you will meet most often are Q4_K_M (25162), Q8_0 (17547), Q5_K_M (17372) and Q6_K (17237), where the number is how many models offer that quant.
Frequently asked questions
Which Qwen GGUF should I download?
The most downloaded Qwen GGUF here is Qwen3.8 Flash Next GSQ RCO. 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 Qwen model need?
Q4_K_M files of Qwen models on this site range from 0.0 to 1481.4 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 Qwen GGUF files come from?
The most common quantizers here are mradermacher, Thireus and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.