GGUF models by RichardErkhov

14354 GGUF models quantized by RichardErkhov on Hugging Face. Sizes run from 1M to 316B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Locutusque Llama 3 Yggdrasil 2.0 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
IS
Isaak Carter J.O.S.I.E.3 Beta10 7B slerp
Isaak · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Sakura SOLRCA Math Instruct DPO v1
Sakura · RichardErkhov
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
PH
Phi 3 Mini 4k Instruct
Phi · RichardErkhov
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
QW
TechxGenus CursorCore QW2.5 1.5B SR
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
LL
Llama 3.2 1B Instruct Ja Version3
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
llama2_koen_13b_SFTtrain
Llama · RichardErkhov
Params13.2B
Context2K
Q4_K_M8.0 GB
GGUF
SI
SiliangZ IRL Iter0 Policy Epoch5 RM Data SPIN Iter0
Siliangz · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Open_Llama_3B_V2
Llama · RichardErkhov
Params3.43B
Context2K
Q4_K_M2.6 GB
GGUF
RY
RyanYr reflect llm8B llmMstlrg om2 80k SftT2 iPSDP20to40kT02 b0.1
Ryanyr · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
MI
WebraftAI synapsellm 7b mistral v0.5 preview2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
mlfoundations dev hp ablations mistral lr5e 6 dcftv1.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2 0.5Bchp 300000
Qwen · RichardErkhov
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
GE
AXCXEPT EZO Common 9B gemma 2 it
Gemma · RichardErkhov
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
PH
JiaweiGuo123 microsoft phi 2 fine tune alpaca chinese merged model
Phi · RichardErkhov
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
LL
mlfoundations dev hp ablations llama3 epoch5 dcftv1.2
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
KA
kavish218 bt generator
Kavish · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
Qwen2-Deita-500m
Qwen · RichardErkhov
Params630M
Context128K
Q4_K_M0.5 GB
GGUF
QW
akshit Gupta qwen new merged FinetunedByAG
Qwen · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
LL
Llama 3 13B
Llama · RichardErkhov
Params13.3B
Context8K
Q4_K_M8.1 GB
GGUF
LL
noaebbot llama3.2 3B insights 16bit resolution
Llama · RichardErkhov
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
CO
CollectiveCognition-v1.1-Nebula-7B
Collectivecognition · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
CodeQwen1.5-7B-Chat
Qwen · RichardErkhov
Params7.25B
Context64K
Q4_K_M4.7 GB
GGUF
SA
saishf Aura Uncensored OAS 8B L3
Saishf · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
PY
Pythia 1b Deduped
Pythia · RichardErkhov
Params1.01B
Context2K
Q4_K_M0.7 GB
GGUF
SM
SmolLM2-135M-Instruct_tldr-sft
SmolLM · RichardErkhov
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
PH
Phi 3.5 Mini Instruct SFT D_chosen Orca Skywork Capybara Infinity Mid3
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
MI
Isotonic Hermes 2 Pro Mixtral 4x7B
Mistral · RichardErkhov
Params24.2B
Context32K
Q4_K_M14.6 GB
Tool use
PY
Pythia 2.8b
Pythia · RichardErkhov
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
GR
GritLM GritLM 7B
Gritlm · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Keep browsing