GGUF models by s3nh

182 GGUF models quantized by s3nh on Hugging Face. Sizes run from 160M to 46.7B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
NS
NSFW-Panda-7B
Nsfw · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AD
AdaptLLM law LLM 13B
Adaptllm · s3nh
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
UT
UTENA-7B-NSFW-V2
Utena · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AD
AdaptLLM finance LLM 13B
Adaptllm · s3nh
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
DE
decapoda research Antares 11b v1
Decapoda · s3nh
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
MI
MiniCPM-2B-dpo-fp32
MiniCPM · s3nh
Params2.72B
Context2K
Q4_K_M1.7 GB
GGUF
AJ
ajibawa 2023 Uncensored Jordan 13B
Ajibawa · s3nh
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NS
s3nh nsfw noromaid zephyr
Nsfw · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AJ
ajibawa 2023 Uncensored Jordan 7B
Ajibawa · s3nh
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
VI
Vikhr-7b-0.1
Vikhr · s3nh
Params7.31B
Context32K
Q4_K_M4.4 GB
GGUF
LL
ehartford WizardLM 1.0 Uncensored Llama2 13b
Llama · s3nh
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
TE
Tess 10.7B v1.5b
Tess · s3nh
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
MI
nsfw-noromaid-mistral-instruct
Mistral · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BitCPM4 CANN 3B
Bitcpm · s3nh
Params3.61B
Context32K
Smallest1.8 GB
GGUF
FI
s3nh Finance Noromaid 13b
Finance · s3nh
Params10.5B
Context2K
Q4_K_M6.3 GB
GGUF
LL
vickt LLama chinese med chat
Llama · s3nh
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
GR
Gryphe MythoMax L2 13b
Gryphe · s3nh
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
NE
NeuralNovel Tanuki 7B v0.1
Neuralnovel · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
WS
WSB GPT 7B
Wsb · s3nh
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
BI
bibidentuhanoi BMO 7B Instruct
Bibidentuhanoi · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AD
AdaptLLM medicine LLM 13B
Adaptllm · s3nh
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
PH
Photolens OpenOrcaxOpenChat 2 13b langchain chat
Photolens · s3nh
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MA
Masterjp123 Clover3 13B
Masterjp · s3nh
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
SA
Sao10K Stheno L2 13B
Sao · s3nh
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
ST
stabilityai japanese stablelm instruct gamma 7b
Stabilityai · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
MathLLM MathCoder CL 7B
Mathllm · s3nh
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
ZE
zephyr-speakleash-007-pl-8192-32-16-0.05
Zephyr · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
CapybaraHermes-2.5-Mistral-7B
Mistral · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
YA
Yash21 TinyYi 7b
Yash · s3nh
Params8.76B
Context32K
Q4_K_M5.3 GB
GGUF
AB
abideen x 7B
Abideen · s3nh
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About s3nh on Hugging Face

s3nh has published 182 GGUF models that ggufmodels.com tracks, across families such as Mistral, Llama and Utena. The most downloaded are NSFW-Panda-7B, AdaptLLM law LLM 13B and UTENA-7B-NSFW-V2.

The quants s3nh publishes most often are Q4_K_M (179), Q8_0 (168), Q6_K (168) and Q3_K_S (168). Their Q4_K_M files range from 0.7 to 28.4 GB. Parameter counts run from 160M to 46.7B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has s3nh published?

182 models are listed here, mainly from the Mistral, Llama and Utena families. The most downloaded is NSFW-Panda-7B.

Which quants does s3nh publish?

The most common are Q4_K_M (179 models), Q8_0 (168 models), Q6_K (168 models) and Q3_K_S (168 models).

Keep browsing