Tinyllama GGUF models
1128 GGUF models in the Tinyllama family, quantized by 406 uploaders. Sizes run from 1M to 8.03B parameters. The longest trained context is 128K tokens.
About the Tinyllama GGUF models
Tinyllama is represented on ggufmodels.com by 1,128 GGUF models, quantized by 406 uploaders on Hugging Face. The most downloaded are tinyllama_tinyllama-1.1b-chat-v1.0, py007_tinyllama-1.1b-chat-v0.3 and TinyLlama 1.1B Chat v0.6. Parameter counts run from 1M to 8.03B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Tinyllama model is between 0.0 to 4.9 GB, which is the quant most people start with. Most files come from mradermacher (189), RichardErkhov (116) and featherless-ai-quants (64). The quants you will meet most often are Q4_K_M (739), Q8_0 (565), Q2_K (508) and Q5_K_M (474), where the number is how many models offer that quant.
Frequently asked questions
Which Tinyllama GGUF should I download?
The most downloaded Tinyllama GGUF here is tinyllama_tinyllama-1.1b-chat-v1.0. 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 Tinyllama model need?
Q4_K_M files of Tinyllama models on this site range from 0.0 to 4.9 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 Tinyllama GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and featherless-ai-quants. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.