Fine GGUF models
83 GGUF models in the Fine family, quantized by 45 uploaders. Sizes run from 9M to 14.8B parameters. The longest trained context is 256K tokens.
About the Fine GGUF models
Fine is represented on ggufmodels.com by 83 GGUF models, quantized by 45 uploaders on Hugging Face. The most downloaded are Fine R1 7B, Fine R1 7B and Fine R1 3B. Parameter counts run from 9M to 14.8B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Fine model is between 0.1 to 9.0 GB, which is the quant most people start with. Most files come from harissonduraes (21), mradermacher (7) and giayphuyen (5). The quants you will meet most often are Q8_0 (45), Q4_K_M (42), Q5_K_M (15) and Q3_K_S (12), where the number is how many models offer that quant.
Frequently asked questions
Which Fine GGUF should I download?
The most downloaded Fine GGUF here is Fine R1 7B. 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 Fine model need?
Q4_K_M files of Fine models on this site range from 0.1 to 9.0 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 Fine GGUF files come from?
The most common quantizers here are harissonduraes, mradermacher and giayphuyen. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.