Broalantaps GGUF models
93 GGUF models in the Broalantaps family, quantized by 1 uploader. Sizes run from 838M to 839M parameters. The longest trained context is 1K tokens.
About the Broalantaps GGUF models
Broalantaps is represented on ggufmodels.com by 93 GGUF models, quantized by 1 uploader on Hugging Face. The most downloaded are BroAlanTaps GPT2 large 64 20000steps, BroAlanTaps GPT2 large 256 16500steps and BroAlanTaps GPT2 large 4 62000steps. Parameter counts run from 838M to 839M, and the longest trained context window is 1K tokens.
A Q4_K_M file of a Broalantaps model is between 0.5 to 0.5 GB, which is the quant most people start with. Most files come from RichardErkhov (93). The quants you will meet most often are Q8_0 (93), Q6_K (93), Q5_K_S (93) and Q5_K_M (93), where the number is how many models offer that quant.
Frequently asked questions
Which Broalantaps GGUF should I download?
The most downloaded Broalantaps GGUF here is BroAlanTaps GPT2 large 64 20000steps. 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 Broalantaps model need?
Q4_K_M files of Broalantaps models on this site range from 0.5 to 0.5 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 Broalantaps GGUF files come from?
The most common quantizers here are 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.