GGUF models: llama3.3 license
790 GGUF models listed under the llama3.3 license on Hugging Face. Always read the license text before commercial use. Sizes run from 14M to 70.6B parameters. The longest trained context is 128K tokens.
LL
Dungeonmaster V2.2 Expanded LLaMa 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
TA
TareksLab L3.3 TRP BASE 80 70B iMat CQ
Tarekslab · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Llama 3.3 70B Instruct
Llama · SandLogicTechnologies
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.3 70B Instruct Q2 K
Llama · j30231
Params70.6B
Context128K
Smallest26.4 GB
LL
Llama 3.3 70B Instruct
Llama · tphage
Params70.6B
Context128K
Smallest43.3 GB
LL
Llama 3.x 70b Triads V8 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Llama 3.3 70b L3.3 NegativeLlama abliterated fusion iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Legion V2.1 LLaMa 70B Elarablated v0.8
Llama · e-n-v-y
Params70.6B
Context128K
Smallest30.9 GB
LL
Aether MS LLaMa 70B
Llama · TareksTesting
Params70.6B
Context128K
Smallest49.9 GB
LL
Llama 3.x 70b Dolnemlimwhitessachi v1.0 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Pathos Alpha LLaMa 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama Poro 2 8B Long Instruct Heretic
Llama · dufuspaelli
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Logos Alpha LLaMa 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.x 70b DoppelGutenberg L3.3 abliterated fusion iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Llama 3.x 70b Gutenberg Doppel L3.3 TDRussel Storywriter abliterated fusion iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LO
L3.3 70B Loki V2.0
Loki · ReadyArt
Params70.6B
Context128K
Smallest60.4 GB
TH
L3.3 The Omega Directive 70B Unslop v2.1 Heretic
The · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.3 70b DarkHorse iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Llama 3.x 70b TrinitEva V1.1 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest52.4 GB
LL
Llama 3.3 Nemotron 70B Instruct Lorablated TA v0.10 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
nvidia Llama 3 3 Nemotron Super 49B v1
Llama · NexesQuants
Params49.9B
Context128K
Smallest53.0 GB
LL
Pathos Beta LLaMa 70B i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.x 70b SmarTricks 0.41 R1 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
llama 3.3 70b q4 k m
Llama · kerncore
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.x 70b FLDx2 Dolphin 128K v1.02 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Dungeonmaster V2 LLaMa 70B i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
DE
DeepSeek V2 Lite Chat Uncensored Unbiased Reasoner
DeepSeek · ijohn07
Params15.7B
Context4K
Smallest16.7 GB
LL
TareksLab Maleficent R1 LLaMa 70B
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
LL
Llama 3.x 70b TessEva 0.1 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB
LL
Llama 3.3 70b Wayfarer Negative fusion v2 iMat CQ
Llama · NexesQuants
Params70.6B
Context128K
Smallest49.6 GB