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
collaiborateorg/Collaiborator-MEDLLM-Llama-3-8B-v1
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Stroganoff
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Code Llama 3 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
PE
L3-Penumbral-Mind-RP-8B
Penumbral · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
LL
PJMixers-Archive/LLaMa-3-CursedStock-v1.6-8B
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Ko Llama3 Luxia 8B i1
Llama · mradermacher
Params8.17B
Context8K
Q4_K_M5.0 GB
GGUF
LL
Llama 3 8B Stroganoff 4.0 Version B
Llama · mradermacher
Params8.03B
Context10K
Q4_K_M4.9 GB
GGUF
LL
Pair Preference Model LLaMA3 8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
aaditya.Llama3 OpenBioLLM 8B
Llama · DevQuasar
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 Preferred MedSwallow 70B
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
CR
crestf411 L3 70B daybreak abliterated v0.4
Crestf · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
gradientai/Llama-3-8B-Instruct-Gradient-1048k
Llama · featherless-ai-quants
Params8.03B
Context1024K
Q4_K_M4.9 GB
GGUF
LL
DeepHermes Egregore v1 RLAIF 8b Atropos
Llama · NousResearch
Params8.03B
Context128K
Smallest4.7 GB
ReasoningTool use
LL
simonycl llama 3 8b instruct agg judge
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Instruct Coding Expert
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
DI
Discord Micae Hermes 3 3B
Discord · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
UM
L3-Umbral-Mind-RP-v3-8B
Umbral · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
UM
L3-Umbral-Mind-RP-v1.0.1-8B
Umbral · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Roleplay
UN
L3-Uncen-Merger-Omelette-RP-v0.1-8B
Uncen · mradermacher
Params8.03B
Context32K
Q4_K_M4.9 GB
Roleplay
LL
LLama 3 8B Tele It
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
CardinalOperations/ORLM-LLaMA-3-8B
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
KingNish Llama3 12b
Llama · RichardErkhov
Params11.5B
Context8K
Q4_K_M7.0 GB
GGUF
LL
elinas/Llama-3-15B-Instruct-zeroed
Llama · featherless-ai-quants
Params15B
Context8K
Q4_K_M9.1 GB
GGUF
LL
DeepMount00.Llama 3 8b Ita
Llama · DevQuasar
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
Lilitu L3.3 70b 0.1
Lilitu · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
AR
Arcee SuperNova v1
Arcee · arcee-ai
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
SL
L3.1 8B Slush v1.1
Slush · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
AE
L3 Aethora 15B
Aethora · QuantFactory
Params15B
Context8K
Q4_K_M9.1 GB
GGUF
LL
Meta Llama 3 70B Instruct
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
MY
Mythorica L3 8B
Mythorica · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF

Keep browsing