GGUF models: llama3.1 license

3570 GGUF models listed under the llama3.1 license on Hugging Face. Always read the license text before commercial use. Sizes run from 3M to 410B parameters. The longest trained context is 4192K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama3.1 70B ShiningValiant2
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
ML
mlfoundations dev dcft orca agentinstruct 1M v1 cleaned singleturn
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Meta llama.Llama Guard 3 8B
Llama · DevQuasar-8
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama SEA LION v3 8B IT Magic_decensored
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
ML
mlfoundations dev OH DCFT V3 wo slimorca 550k
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Natsumura Llama3.1 Base 8b
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B FlashNorm
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama PLLuM 70B Instruct
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · EasierAI
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LL
Llama3.1 8b Cpt Sea Lionv3 Base
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Cogito v2 Preview Llama 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
LW
LwQ Reasoner 10B
Lwq · mradermacher
Params10.3B
Context32K
Q4_K_M6.3 GB
GGUF
LL
Dobby Mini Unhinged Llama 3.1 8B
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
RoleplayTool use
LL
mlfoundations dev llama3 1 8b mlfoundations dev stackexchange politics
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Zhengyi/LLaMA-Mesh
Llama · featherless-ai-quants
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 Tulu 3 405B
Llama · lmstudio-community
Params405B
Context128K
Q4_K_M243.1 GB
GGUF
LL
Llama3.1 8B Chinese Chat
Llama · gaianet
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama3.1 8B Esper2
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingTool use
ML
mlfoundations dev oh teknium scaling down ratiocontrolled 0.7
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DC
oh dcft v1.3 no curation gpt 4o mini scale 4x
Dcft · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama PLLuM 8B Chat 2512
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
DE
DeepSeek R1 Distill Llama UK Legislation 8B
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LL
MFANN llama3.1 abliterated SLERP v3
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
WaRP Safety Llama3_8B_Instruct 20251027_125759
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3.1 8B ArliAI RPMax v1.3
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
oh dcft v3.1 llama 3.1 8b i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
VA
VaryTales 8b i1
Varytales · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3.1 8b Instruct
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
DarkIdol Llama 3.1 8B Instruct 1.2 Uncensored
Llama · happenmajic89
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay

Keep browsing