Yanoljanext GGUF models

70 GGUF models in the Yanoljanext family, quantized by 37 uploaders. Sizes run from 2.82B to 28.4B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · bartowski
Params12.8B
Context128K
Q4_K_M7.9 GB
GGUF
YA
YanoljaNEXT Rosetta 27B 2511
Yanoljanext · mradermacher
Params28.4B
Context128K
Q4_K_M17.3 GB
GGUF
YA
EEVE Korean Instruct 10.8B v1.0
Yanoljanext · teddylee777
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · mradermacher
Params12.8B
Context128K
Q4_K_M7.9 GB
GGUF
YA
YanoljaNEXT Rosetta 4B 2511
Yanoljanext · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
YA
EEVE Korean 10.8B v1.0
Yanoljanext · mradermacher
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
YA
YanoljaNEXT EEVE Rosetta 7B 2602
Yanoljanext · mradermacher
Params8.3B
Context32K
Q4_K_M5.1 GB
GGUF
YA
EEVE Korean 10.8B v1.0
Yanoljanext · mradermacher
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
YA
YanoljaNEXT Rosetta 20B
Yanoljanext · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
YA
YanoljaNEXT Rosetta 27B 2511
Yanoljanext · mradermacher
Params28.4B
Context128K
Q4_K_M17.3 GB
GGUF
YA
YanoljaNEXT Rosetta 4B 2511
Yanoljanext · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
YA
YanoljaNEXT Rosetta 12B
Yanoljanext · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
YA
YanoljaNEXT EEVE Rosetta 7B 2602
Yanoljanext · mradermacher
Params8.3B
Context32K
Q4_K_M5.1 GB
GGUF
YA
YanoljaNEXT Rosetta 20B
Yanoljanext · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
YA
EEVE Korean Instruct 7B v2.0 Preview
Yanoljanext · mradermacher
Params7.66B
Context32K
Q4_K_M4.7 GB
Tool use
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · mradermacher
Params12.8B
Context128K
Q4_K_M7.9 GB
GGUF
YA
EEVE Korean Instruct 10.8B v1.0
Yanoljanext · tensorblock
Params10.8B
Context4K
Smallest4.0 GB
GGUF
YA
EEVE Korean Instruct 2.8B v1.0 Q4 K M
Yanoljanext · andreass123
Params2.82B
Context2K
Q4_K_M1.8 GB
GGUF
YA
EEVE Korean Judgment Transducer 10.8B v2.0
Yanoljanext · Suchae
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
YA
EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF
Yanoljanext · Suchae
Params10.8B
Context4K
Smallest21.6 GB
GGUF
YA
EEVE Korean 10.8B v1.0
Yanoljanext · tensorblock
Params10.8B
Context4K
Smallest4.0 GB
GGUF
YA
EEVE-Korean-Instruct-10.8B-v1.0-saemzzang2-q4_k_s-gguf
Yanoljanext · saemzzang
Params10.8B
Context4K
Smallest6.2 GB
GGUF
YA
EEVE-Korean-Instruct-10.8B-v1.0
Yanoljanext · AIRider
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
YA
EEVE Korean Instruct 2.8B v1.0 Q8 0
Yanoljanext · andreass123
Params2.82B
Context2K
Smallest3.0 GB
GGUF
YA
YanoljaNEXT Rosetta 12B
Yanoljanext · NikolayKozloff
Params11.8B
Context128K
Smallest9.7 GB
GGUF
YA
EEVE Korean Instruct 10.8B v1.0 Q5 K M
Yanoljanext · SourPineapple
Params10.8B
Context4K
Smallest7.7 GB
GGUF
YA
EEVE Ko 8B Instruct hr 250121 ver2 test
Yanoljanext · ragbox
Params10.8B
Context4K
Smallest11.5 GB
GGUF
YA
YanoljaNEXT Rosetta 12B
Yanoljanext · NikolayKozloff
Params11.8B
Context128K
Smallest12.5 GB
GGUF
YA
EEVE Korean Instruct 10.8B v1.0
Yanoljanext · js2jang
Params10.8B
Context4K
Smallest6.1 GB
GGUF
YA
EEVE-Korean-10.8B-v1.0
Yanoljanext · geonheechoi22
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF

About the Yanoljanext GGUF models

Yanoljanext is represented on ggufmodels.com by 70 GGUF models, quantized by 37 uploaders on Hugging Face. The most downloaded are YanoljaNEXT Rosetta 12B 2510, YanoljaNEXT Rosetta 27B 2511 and EEVE Korean Instruct 10.8B v1.0. Parameter counts run from 2.82B to 28.4B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Yanoljanext model is between 1.8 to 17.3 GB, which is the quant most people start with. Most files come from mradermacher (14), NikolayKozloff (10) and ragbox (3). The quants you will meet most often are Q4_K_M (40), Q8_0 (23), Q5_K_M (23) and Q6_K (20), where the number is how many models offer that quant.

Frequently asked questions

Which Yanoljanext GGUF should I download?

The most downloaded Yanoljanext GGUF here is YanoljaNEXT Rosetta 12B 2510. 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 Yanoljanext model need?

Q4_K_M files of Yanoljanext models on this site range from 1.8 to 17.3 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 Yanoljanext GGUF files come from?

The most common quantizers here are mradermacher, NikolayKozloff and ragbox. 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