GGUF models: llama3 license

3439 GGUF models listed under the llama3 license on Hugging Face. Always read the license text before commercial use. Sizes run from 7M to 406B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
HiroseKoichi/Llama-3-8B-Stroganoff-2.0
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Ko 8B Instruct AOG
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CE
nothingiisreal/L3-8B-Celeste-V1.2
Celeste · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
UM
Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
Umbral · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
HE
L3 Hecate 8B v1.1
Hecate · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 OpenBioLLM 8B Q8 0
Llama · jorgedelpozolerida
Params8.03B
Context8K
Smallest8.5 GB
GGUF
LL
picAIso TARS 8B llama TIEMIX
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-70B-Instruct-Gradient-1048k
Llama · vsevolodl
Params70.6B
Context1024K
Q4_K_M42.5 GB
GGUF
LL
RLHFlow/pair-preference-model-LLaMA3-8B
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
1min-v2-luxia-8b
Min · mradermacher
Params8.17B
Context8K
Q4_K_M5.0 GB
GGUF
TR
Trickser Theta 4 70B calibrated
Trickster · Babsie
Params70.6B
Context128K
Smallest49.9 GB
ReasoningRoleplayTool use
LL
Magpie Align Llama 3 8B OpenHermes 243K
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
LL
Llama-3-3x8B-multilingual
Llama · mradermacher
Params19.3B
Context80K
Q4_K_M11.7 GB
GGUF
LL
Llama 3 8B Ultra Instruct SaltSprinkle
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Instruct japanese nk2t v0.2
Llama · nk2t
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3-ChatQA-1.5-8B
Llama · narainp
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3 8B
Llama · kaetemi
Params8.03B
Context8K
Smallest4.7 GB
GGUF
LL
aixsatoshi/Llama-3-youko-8b-instruct-chatvector
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-8B-Instruct-Gradient-1048k
Llama · jpodivin
Params8.03B
Context1024K
Smallest5.7 GB
GGUF
LL
OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
ytu-ce-cosmos/Turkish-Llama-8b-v0.1
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
dfurman Llama 3 70B Orpo v0.1
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
VIRNECT/llama-3-Korean-8B-V3
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
louisbrulenaudet/Romulus-cpt-Llama-3.1-8B-v0.1-Instruct
Llama · featherless-ai-quants
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama3 8b Cpt Sahabatai v1 Instruct
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
ArliAI/ArliAI-Llama-3-8B-Formax-v1.0
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
NE
Daredevil 8B Abliterated
Neuraldaredevil · sathya801
Params8.03B
Context8K
Smallest5.7 GB
GGUF
LL
shisa-v1-llama3-8b
Llama · shisa-ai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Keep browsing