Ling GGUF models
219 GGUF models in the Ling family, quantized by 70 uploaders. Sizes run from 4M to 1000B parameters. The longest trained context is 256K tokens.
About the Ling GGUF models
Ling is represented on ggufmodels.com by 219 GGUF models, quantized by 70 uploaders on Hugging Face. The most downloaded are Ling 3.0 Tiny, Ling 3.0 Flash and Ling 3.0 Flash Dspark. Parameter counts run from 4M to 1000B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Ling model is between 0.7 to 608.4 GB, which is the quant most people start with. Most files come from mradermacher (49), Manojb (34) and kingjones777 (13). The quants you will meet most often are Q4_K_M (116), Q5_K_M (101), Q6_K (86) and Q3_K_M (86), where the number is how many models offer that quant.
Frequently asked questions
Which Ling GGUF should I download?
The most downloaded Ling GGUF here is Ling 3.0 Tiny. 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 Ling model need?
Q4_K_M files of Ling models on this site range from 0.7 to 608.4 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 Ling GGUF files come from?
The most common quantizers here are mradermacher, Manojb and kingjones777. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.