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
Meta-Llama-3-8B
Llama · fanrey
Params8.03B
Context8K
Q4_K_M9.8 GB
GGUF
LL
Kancil V1 llama3 fp16
Llama · MaziyarPanahi
Params8.03B
Context8K
Smallest5.6 GB
GGUF
MA
MARS v0.2
Mars · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
JA
Jamet 8B L3 MK.V Blackroot
Jamet · backyardai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
VI
VietHealth GPT 8B 202406
Viethealth · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3
Llama · featherless-ai-quants
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-Yggdrasil-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Awanllm-Llama-3-8B-Dolfin-v1.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama3-8B-DarkIdol-2.1-Uncensored-32K
Llama · victorbur
Params8.03B
Context128K
Smallest5.7 GB
Roleplay
LL
anakin87/Llama-3-8b-ita-ties-pro
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ET
EtherealRainbow-v0.3-8B
Etherealrainbow · invisietch
Params8.03B
Context8K
Smallest4.7 GB
GGUF
LL
Iamsahinemir Meta Llama
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Llama3 OpenBioLLM 8B
Llama · hdnh2006
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Kor BCCard
Llama · sh2orc
Params11.7B
Context8K
Smallest12.4 GB
GGUF
LL
Llama-3-70B-Instruct-v0.1
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama 3 Galen 8B 32k v1
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Llama 3 8B Magpie Air SFT v0.1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-8B-Magpie-Pro-MT-UltraDPO
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-8B-Web
Llama · MoMonir
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta-Llama-3-70B-Instruct
Llama · seawolf2357
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Orion-zhen/Llama3-70B-Orion-Chinese
Llama · featherless-ai-quants
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Magpie Align v0.3
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
Reasoning
LL
Hermes 3 Llama 3.1 8B
Llama · Tho465
Params8.03B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
LL
Llama 3 70B Orpo v0.1
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
LL
Llama-3-8B-Lexi-Uncensored
Llama · cminja
Params8.03B
Context8K
Smallest8.5 GB
GGUF
LL
Meta-Llama-3-70B-Instruct
Llama · aiqtech
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
RE
RemixLlama3-8B
Remixllama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Keep browsing