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.
LL
swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
New Dawn Llama3 70b 32K v1.0
Llama · RichardErkhov
Params70.6B
Context32K
Q4_K_M42.5 GB
LL
fireworks-ai/llama-3-firefunction-v2
Llama · featherless-ai-quants
Params70.6B
Context8K
Q4_K_M42.5 GB
LL
Abacusai Smaug Llama 3 70B Instruct 32K
Llama · tensorblock
Params70.6B
Context32K
Smallest26.4 GB
LL
Llama 3 8B Instruct GGUF Q4 K M
Llama · thesven
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
anakin87 Llama 3 8b ita slerp
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
anakin87 yo Llama 3 8B Instruct
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama-3-8B-Instruct-abliterated-v2
Llama · QuixiAI
Params8.03B
Context8K
Smallest4.0 GB
LL
Turkish-Llama-8b-v0.1
Llama · LiteLLMs
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama-3-Elyza-Youko-moe-2x8B
Llama · mradermacher
Params13.7B
Context8K
Q4_K_M8.3 GB
LL
Llama-3-Umbral-Mind-Instruct-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
VIRNECT llama 3 Korean 8B r v2
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
LLaMA3-iterative-DPO-final-ExPO
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
CE
L3-8B-Celeste-v1
Celeste · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3 8B Stroganoff 2.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
HE
Hermes 4 70B
Hermes · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
TY
L3-Tyche-8B-v1.0
Tyche · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llama3 8B DWP
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
UM
L3 Umbral Mind RP v0.3 8B
Umbral · l3utterfly
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
DarkIdol Llama 3.1 8B Instruct 1.0 Uncensored
Llama · MaziyarPanahi
Params8.03B
Context128K
Q4_K_M4.9 GB
ME
ProbeMedicalYonseiMAILab.medllama3 v20
Medllama · DevQuasar-8
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llama3 8b 1048k i1
Llama · mradermacher
Params8.03B
Context1024K
Q4_K_M4.9 GB
LL
unsloth/llama-3-8b
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3 Swallow 70B Instruct v0.1
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
LL
Meta Llama 3 8B Instruct
Llama · SkyNotion
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
merge passthrough Meta Llama 3 Instruct 10B
Llama · mradermacher
Params9.78B
Context8K
Q4_K_M6.0 GB
RE
T Rex mini I1
Rex · Deaquay
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Smaug Llama 3 70B Instruct
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
LL
Halu-8B-Llama3-Blackroot
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Tess 2.0 Llama 3 8B
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB