Breeze GGUF models
90 GGUF models in the Breeze family, quantized by 36 uploaders. Sizes run from 21M to 12.7B parameters. The longest trained context is 128K tokens.
About the Breeze GGUF models
Breeze is represented on ggufmodels.com by 90 GGUF models, quantized by 36 uploaders on Hugging Face. The most downloaded are Breeze-TTS-2, Breeze-ASR-25 and breeze-tts-2. Parameter counts run from 21M to 12.7B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Breeze model is between 1.0 to 7.7 GB, which is the quant most people start with. Most files come from mradermacher (28), CHE-72 (11) and RichardErkhov (6). The quants you will meet most often are Q6_K (55), Q4_K_M (55), Q5_K_M (54) and Q8_0 (48), where the number is how many models offer that quant.
Frequently asked questions
Which Breeze GGUF should I download?
The most downloaded Breeze GGUF here is Breeze-TTS-2. 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 Breeze model need?
Q4_K_M files of Breeze models on this site range from 1.0 to 7.7 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 Breeze GGUF files come from?
The most common quantizers here are mradermacher, CHE-72 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.