GGUF models by LoneStriker
163 GGUF models quantized by LoneStriker on Hugging Face. Sizes run from 1.1B to 236B parameters. The longest trained context is 1024K tokens.
BE
34b beta
Beta · LoneStriker
Params34.4B
Context195K
Q4_K_M20.7 GB
SO
Solstice 11B v1
Solstice · LoneStriker
Params10.7B
Context4K
Q4_K_M6.5 GB
BO
BoreanGale 70B
Boreangale · LoneStriker
Params69B
Context32K
Q4_K_M41.4 GB
NX
Nxcode-CQ-7B-orpo
Nxcode · LoneStriker
Params7.25B
Context64K
Q4_K_M4.7 GB
QW
firefly-qwen1.5-en-7b
Qwen · LoneStriker
Params7.72B
Context32K
Q4_K_M4.8 GB
GO
Gorgon 7b v0.1
Gorgon · LoneStriker
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
Gemmalpaca-7B
Gemma · LoneStriker
Params8.54B
Context8K
Q4_K_M5.3 GB
HU
HuginnV5.5 12.6B
Huginnv · LoneStriker
Params12.9B
Context32K
Q4_K_M7.8 GB
MI
openbuddy mistral 10b v17.1 32k
Mistral · LoneStriker
Params10.8B
Context32K
Q4_K_M6.5 GB
TE
Tess 72B v1.5b
Tess · LoneStriker
Params72.3B
Context32K
Q4_K_M43.8 GB
LL
Meta-Llama-3-8B-Instruct-LessResistant
Llama · LoneStriker
Params8.03B
Context8K
Q4_K_M4.9 GB
TR
Trinity 33B v1.0
Trinity · LoneStriker
Params33.3B
Context16K
Q4_K_M19.9 GB
SA
Samantha 120b
Samantha · LoneStriker
Params120B
Context4K
Smallest44.2 GB