Xlam GGUF models
85 GGUF models in the Xlam family, quantized by 31 uploaders. Sizes run from 91M to 141B parameters. The longest trained context is 128K tokens.
About the Xlam GGUF models
Xlam is represented on ggufmodels.com by 85 GGUF models, quantized by 31 uploaders on Hugging Face. The most downloaded are xLAM 8x7b R, xLAM 8x22b R and xLAM 2 3b Fc R. Parameter counts run from 91M to 141B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Xlam model is between 0.9 to 85.6 GB, which is the quant most people start with. Most files come from mradermacher (13), microtensor-archive (7) and tensorblock (5). The quants you will meet most often are Q4_K_M (58), Q2_K (55), Q8_0 (52) and Q6_K (51), where the number is how many models offer that quant.
Frequently asked questions
Which Xlam GGUF should I download?
The most downloaded Xlam GGUF here is xLAM 8x7b R. 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 Xlam model need?
Q4_K_M files of Xlam models on this site range from 0.9 to 85.6 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 Xlam GGUF files come from?
The most common quantizers here are mradermacher, microtensor-archive and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.