Open GGUF models
117 GGUF models in the Open family, quantized by 36 uploaders. Sizes run from 135M to 65B parameters. The longest trained context is 128K tokens.
About the Open GGUF models
Open is represented on ggufmodels.com by 117 GGUF models, quantized by 36 uploaders on Hugging Face. The most downloaded are rombodawg_open_gpt4_8x7b, rombodawg_open_gpt4_8x7b_v0.2 and s4sch_open-hermes-2.5-neural-chat-3.1-frankenmerge-11b. Parameter counts run from 135M to 65B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Open model is between 0.1 to 39.3 GB, which is the quant most people start with. Most files come from mradermacher (49), tensorblock (12) and RichardErkhov (7). The quants you will meet most often are Q2_K (95), Q4_K_M (89), Q5_K_M (83) and Q3_K_M (83), where the number is how many models offer that quant.
Frequently asked questions
Which Open GGUF should I download?
The most downloaded Open GGUF here is rombodawg_open_gpt4_8x7b. 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 Open model need?
Q4_K_M files of Open models on this site range from 0.1 to 39.3 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 Open GGUF files come from?
The most common quantizers here are mradermacher, tensorblock 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.