Falcon GGUF models
576 GGUF models in the Falcon family, quantized by 124 uploaders. Sizes run from 4M to 180B parameters. The longest trained context is 1024K tokens.
About the Falcon GGUF models
Falcon is represented on ggufmodels.com by 576 GGUF models, quantized by 124 uploaders on Hugging Face. The most downloaded are Jiqing tiny random falcon, Falcon H1R 7B and 90m Instruct. Parameter counts run from 4M to 180B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Falcon model is between 0.0 to 26.0 GB, which is the quant most people start with. Most files come from mradermacher (186), tiiuae (32) and maddes8cht (27). The quants you will meet most often are Q4_K_M (422), Q5_K_M (370), Q6_K (358) and Q8_0 (339), where the number is how many models offer that quant.
Frequently asked questions
Which Falcon GGUF should I download?
The most downloaded Falcon GGUF here is Jiqing tiny random falcon. 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 Falcon model need?
Q4_K_M files of Falcon models on this site range from 0.0 to 26.0 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 Falcon GGUF files come from?
The most common quantizers here are mradermacher, tiiuae and maddes8cht. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.