GGUF models by adamksn

34 GGUF models quantized by adamksn on Hugging Face. Sizes run from 7.24B to 12.9B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
Mistral 7B Sunda v1.0
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
PA
Pastiche Crown Clown 7B dare
Pastiche · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AL
NeuralMaxime 7B slerp
Alphamonarch · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZY
ZySec 7B v1
Zysec · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
CA
CarbonBeagle 11B truthy
Carbonbeagle · adamksn
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
MI
Mistral CatMacaroni slerp uncensored 7B
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Saul Instruct v1
Saul · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NE
Turdus 7B
Neuralmarcoro · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral 7B v0.1
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
NeuralHermes 2.5 Mistral 7B
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
SO
SOLAR 10.7B Instruct v1.0 uncensored
Solar · adamksn
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
NO
Nous Hermes 2 SOLAR 10.7B misaligned
Nous · adamksn
Params10.7B
Context4K
Q4_K_M6.5 GB
Tool use
LL
Llama 3.1 8B Lexi Uncensored
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
GGUF
LL
Llama 3.1 8B ArliAI Indo Formax v1.0
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
GGUF
LL
Llama3.1 8B Cobalt
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
Tool use
LL
dolphin 2.9.4 llama3.1 8b
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
Coding
LL
Llama 3.1 8B ArliAI Formax v1.0
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
GGUF
MI
Mistral 7B Instruct v0.2
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama3.1 8B Enigma
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
CodingTool use
LL
Llama3.1 8B Fireplace2
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
Tool use
FU
FuseChat 7B VaRM
Fusechat · adamksn
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
DO
Dolphin 2.8 Experiment26 7B
Dolphin · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingTool use
MI
Garten2 7B
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Hermes 2 Theta Llama 3 8B 32k
Llama · adamksn
Params8.03B
Context32K
Smallest3.2 GB
Tool use
LL
BRAG Llama 3.1 8b v0.1
Llama · adamksn
Params8.03B
Context128K
Smallest3.2 GB
GGUF
TR
Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B
Truthful · adamksn
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
MI
Genstruct 7B
Mistral · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZY
ZySec 7B v2
Zysec · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama 3 Smaug 8B
Llama · adamksn
Params8.03B
Context8K
Smallest3.2 GB
GGUF
NE
NeuralDarewin 7B
Neuraldarewin · adamksn
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About adamksn on Hugging Face

adamksn has published 34 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and Zysec. The most downloaded are Mistral 7B Sunda v1.0, Pastiche Crown Clown 7B dare and NeuralMaxime 7B slerp.

The quants adamksn publishes most often are Q8_0 (34), Q6_K (34), Q4_0 (34) and Q5_K_M (23). Their Q4_K_M files range from 4.4 to 7.8 GB. Parameter counts run from 7.24B to 12.9B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has adamksn published?

34 models are listed here, mainly from the Llama, Mistral and Zysec families. The most downloaded is Mistral 7B Sunda v1.0.

Which quants does adamksn publish?

The most common are Q8_0 (34 models), Q6_K (34 models), Q4_0 (34 models) and Q5_K_M (23 models).

Keep browsing