Mergekit GGUF models

221 GGUF models in the Mergekit family, quantized by 28 uploaders. Sizes run from 323M to 34.4B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ME
mergekit dare ties ymiqjtz
Mergekit · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
Mergekit Dare_Ties Twfgema
Mergekit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ME
mergekit slerp xlblwaw i1
Mergekit · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
ME
mergekit community mergekit task arithmetic jaowyfi
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
Mergekit Sce Sudfgqi
Mergekit · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
ReasoningTool use
ME
Mergekit Passthrough Hdctkvu
Mergekit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ME
mergekit model stock tiwlqms i1
Mergekit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ME
mergekit community mergekit model stock hxpoald
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit model stock ysywggg i1
Mergekit · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community mergekit slerp janrfan
Mergekit · RichardErkhov
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community mergekit slerp iyanrea
Mergekit · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
mergekit slerp exkkzvd
Mergekit · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
mergekit community Mathing 1.5B
Mergekit · RichardErkhov
Params1.59B
Context32K
Q4_K_M1.0 GB
GGUF
ME
mergekit community config smart ablit
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community mergekit slerp tsuvyfz
Mergekit · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
mergekit community mergekit ties rsmvina
Mergekit · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
ME
mergekit community mergekit slerp duaqshp
Mergekit · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
mergekit community mergekit della linear aydsqju
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
ME
mergekit model stock fpfjlqs i1
Mergekit · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community mergekit model stock anvdilz
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community mergekit model stock fhjvgqq
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community L3.1 Artemis c 8B
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit community final test 4 v2 original old recipe humanish base
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ME
mergekit model stock rxbbxes i1
Mergekit · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ME
Mergekit Dare_Ties Tpraytl
Mergekit · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
ME
mergekit community mergekit linear ugyqudc
Mergekit · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
ME
mergekit community mergekit della linear uogzotg
Mergekit · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
ME
mergekit community mergekit ties hmuospj
Mergekit · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ME
Mergekit Model_Stock Qtseiad
Mergekit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ME
mergekit community mergekit ties jsvenvj
Mergekit · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About the Mergekit GGUF models

Mergekit is represented on ggufmodels.com by 221 GGUF models, quantized by 28 uploaders on Hugging Face. The most downloaded are mergekit dare ties ymiqjtz, Mergekit Dare_Ties Twfgema and mergekit slerp xlblwaw i1. Parameter counts run from 323M to 34.4B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Mergekit model is between 0.5 to 41.3 GB, which is the quant most people start with. Most files come from RichardErkhov (66), mradermacher (38) and fengpeisheng1 (15). The quants you will meet most often are Q4_K_M (129), Q2_K (126), Q3_K_M (118) and Q5_K_M (109), where the number is how many models offer that quant.

Frequently asked questions

Which Mergekit GGUF should I download?

The most downloaded Mergekit GGUF here is mergekit dare ties ymiqjtz. 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 Mergekit model need?

Q4_K_M files of Mergekit models on this site range from 0.5 to 41.3 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 Mergekit GGUF files come from?

The most common quantizers here are RichardErkhov, mradermacher and fengpeisheng1. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing