GGUF models by QuantFactory
1418 GGUF models quantized by QuantFactory on Hugging Face. Sizes run from 9M to 225B parameters. The longest trained context is 4194304K tokens.
CE
L3 8B Celeste v1
Celeste · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen2 7b Matter 0.1 Slim A
Qwen · QuantFactory
Params7.62B
Context128K
Q4_K_M4.7 GB
LL
Albatross2.1 8B Instruct
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
GR
granite 3.1 3b a800m instruct
Granite · QuantFactory
Params3.37B
Context128K
Q4_K_M2.1 GB
LL
Llama 3.2 3B Overthinker
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
MI
Book Gut12B
Mistral · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
NI
Ninja V2 7B
Ninja · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
DA
MN Dark Planet TITAN 12B
Dark · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
AR
Art v0 3B
Art · QuantFactory
Params3.4B
Context32K
Q4_K_M2.1 GB
NE
Nemomix v2.0 12B
Nemomix · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
CR
Crimson_Dawn v0.2 Base
Crimson · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
LL
Llama 3.1 Tulu 3 8B DPO
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
CH
Chocolatine 3B Instruct DPO Revised
Chocolatine · QuantFactory
Params3.82B
Context4K
Q4_K_M2.4 GB
LL
Llama 3.1 Swallow 8B v0.1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
SM
Smegmma 9B v1
Smegmma · QuantFactory
Params9.24B
Context8K
Q4_K_M5.8 GB
AZ
Azure Dusk v0.1
Azure · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Datarus R1 14B preview
Qwen · QuantFactory
Params14.8B
Context128K
Q4_K_M9.0 GB
OL
AMD OLMo 1B SFT DPO
OLMo · QuantFactory
Params1.18B
Context2K
Q4_K_M0.7 GB
GE
Gemma 2 Ataraxy v4 Advanced 9B
Gemma · QuantFactory
Params9.24B
Context8K
Q4_K_M5.8 GB
MI
Mahou Gutenberg Nemo 12B
Mistral · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
LL
ArliAI Llama 3 8B Instruct ORPO v0.1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
CL
ClinicalGPT base zh
Clinicalgpt · QuantFactory
Params8.1B
Context4K
Q4_K_M5.3 GB
LL
llama 3 8b chat reglamentacion V1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
DE
deepseek llm 7b base
DeepSeek · QuantFactory
Params6.91B
Context4K
Q4_K_M4.2 GB
YU
YuE s1 7B anneal en cot
Yue · QuantFactory
Params6.22B
Context16K
Q4_K_M3.8 GB
VI
st vicuna v1.3 10.5b taylor
Vicuna · QuantFactory
Params10.5B
Context2K
Q4_K_M6.3 GB
LL
ArliAI Llama 3 8B Cumulus v0.3
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
EE
EEVE Korean Instruct 10.8B v1.0
Eeve · QuantFactory
Params10.8B
Context4K
Q4_K_M6.5 GB
LL
Reasoning Llama 3b v0.1
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
MI
OmniLing V1 12b experimental
Mistral · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB