Parakeet GGUF models
155 GGUF models in the Parakeet family, quantized by 66 uploaders. Sizes run from 18M to 1.07B parameters.
About the Parakeet GGUF models
Parakeet is represented on ggufmodels.com by 155 GGUF models, quantized by 66 uploaders on Hugging Face. The most downloaded are Parakeet Unified EN 0.6B, Parakeet TDT 0.6B v3 and parakeet-tdt-0.6b-v3.oss-align.q8_0. Parameter counts run from 18M to 1.07B.
A Q4_K_M file of a Parakeet model is between 0.1 to 0.8 GB, which is the quant most people start with. Most files come from cstr (15), handy-computer (12) and voicetide (11). The quants you will meet most often are Q8_0 (124), F16 (51), Q5_K_M (45) and Q4_K_M (38), where the number is how many models offer that quant.
Frequently asked questions
Which Parakeet GGUF should I download?
The most downloaded Parakeet GGUF here is Parakeet Unified EN 0.6B. 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 Parakeet model need?
Q4_K_M files of Parakeet models on this site range from 0.1 to 0.8 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 Parakeet GGUF files come from?
The most common quantizers here are cstr, handy-computer and voicetide. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.