Dolphin GGUF models
95 GGUF models in the Dolphin family, quantized by 34 uploaders. Sizes run from 386M to 69B parameters. The longest trained context is 1024K tokens.
About the Dolphin GGUF models
Dolphin is represented on ggufmodels.com by 95 GGUF models, quantized by 34 uploaders on Hugging Face. The most downloaded are Dolphin3 Cyber 8B, Dolphin X1 8B and weyaxi_dolphin2.1-openorca-7b. Parameter counts run from 386M to 69B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Dolphin model is between 1.9 to 41.4 GB, which is the quant most people start with. Most files come from mradermacher (50), harkov000 (4) and RichardErkhov (4). The quants you will meet most often are Q4_K_M (79), Q5_K_M (77), Q2_K (70) and Q6_K (69), where the number is how many models offer that quant.
Frequently asked questions
Which Dolphin GGUF should I download?
The most downloaded Dolphin GGUF here is Dolphin3 Cyber 8B. 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 Dolphin model need?
Q4_K_M files of Dolphin models on this site range from 1.9 to 41.4 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 Dolphin GGUF files come from?
The most common quantizers here are mradermacher, harkov000 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.