Test GGUF models
486 GGUF models in the Test family, quantized by 342 uploaders. Sizes run from 1M to 284B parameters. The longest trained context is 1024K tokens.
About the Test GGUF models
Test is represented on ggufmodels.com by 486 GGUF models, quantized by 342 uploaders on Hugging Face. The most downloaded are test model router download, test gguf sample and test model stories260K. Parameter counts run from 1M to 284B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Test model is between 0.0 to 72.9 GB, which is the quant most people start with. Most files come from tensorblock (14), featherless-ai-quants (10) and shidowake (9). The quants you will meet most often are Q8_0 (188), Q4_K_M (186), F16 (77) and Q5_K_M (74), where the number is how many models offer that quant.
Frequently asked questions
Which Test GGUF should I download?
The most downloaded Test GGUF here is test model router download. 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 Test model need?
Q4_K_M files of Test models on this site range from 0.0 to 72.9 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 Test GGUF files come from?
The most common quantizers here are tensorblock, featherless-ai-quants and shidowake. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.