Strangemerges GGUF models
126 GGUF models in the Strangemerges family, quantized by 7 uploaders. Sizes run from 7.24B to 12.9B parameters. The longest trained context is 32K tokens.
About the Strangemerges GGUF models
Strangemerges is represented on ggufmodels.com by 126 GGUF models, quantized by 7 uploaders on Hugging Face. The most downloaded are models--automerger--Inex12Strangemerges_32-7B, models--automerger--Strangemerges_32Shadow-7B and models--automerger--Strangemerges_32Yam-7B. Parameter counts run from 7.24B to 12.9B, and the longest trained context window is 32K tokens.
A Q4_K_M file of a Strangemerges model is between 4.4 to 4.4 GB, which is the quant most people start with. Most files come from Gille (56), mradermacher (44) and MaziyarPanahi (17). The quants you will meet most often are Q4_K_M (125), Q5_K_M (70), Q6_K (68) and Q5_K_S (68), where the number is how many models offer that quant.
Frequently asked questions
Which Strangemerges GGUF should I download?
The most downloaded Strangemerges GGUF here is models--automerger--Inex12Strangemerges_32-7B. 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 Strangemerges model need?
Q4_K_M files of Strangemerges models on this site range from 4.4 to 4.4 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 Strangemerges GGUF files come from?
The most common quantizers here are Gille, mradermacher and MaziyarPanahi. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.