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
abhinand/Llama-3-Galen-8B-32k-v1
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Hermes 3 Llama 3.1 8B
Llama · YorkieOH10
Params8.03B
Context128K
Smallest8.5 GB
RoleplayTool use
LL
TurkLlama Mix
Llama · matrixportalx
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Magpie Air SFT Magpo sfairXC 8B 05
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
teddylee777/Llama-3-Open-Ko-8B-Instruct-teddynote
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
RE
RE 70B AS3D
altomek
Params70.6B
Context128K
Smallest15.3 GB
GGUF
LL
Llama 3 8B UltraMedical
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LU
L3 8B Lunar Stheno
Lunar · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
LLaMA 3 8B SFR Iterative DPO Concise R
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
turboderp/llama3-turbcat-instruct-8b
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Trendyol/Trendyol-LLM-8b-chat-v2.0
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Magpie Align v0.1
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
ArliAI Llama 3 8B Dolfin v0.2 Instruct
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LU
L3 8B Lunaris v1
Lunaris · backyardai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Blackroot/Llama-3-LongStory
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 Preferred MedSwallow 70B
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama 3 15b Instruct
Llama · mradermacher
Params15.4B
Context8K
Q4_K_M9.4 GB
GGUF
LL
Llama 3 8B ArliAI Formax v1.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Locutusque/Llama-3-Yggdrasil-8B
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
nk2t Llama 3 8B Instruct japanese nk2t v0.2
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
BI
BigWeave v33 105b i1
Bigweave · mradermacher
Params105B
Context8K
Smallest22.5 GB
GGUF
LL
cstr llama3 8b spaetzle v20
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
picAIso/TARS-8B-llama-TIEMIX
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
lemon07r/Lllama-3-RedElixir-8B
Lllama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
NaniDAO.Llama 3.3 70B Instruct ablated
Llama · DevQuasar-6
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
flammenai Mahou 1.2a llama3 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
markrodrigo/Llama-3.1-8B-Instruct-Spatial-SQL-1.0
Llama · featherless-ai-quants
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
migtissera/Llama-3-8B-Synthia-v3.5
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
maldv/Meta-Llama-3-8B-Instruct-hf
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Instruct Norefusal
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Keep browsing