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 Instruct ggml model Q4 K M
Llama · nmerkle
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Trendyol LLM 8b Chat v2.0
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
SE
RUN WITH SCISSORS 3.2 1B Q4 K M
Sentimental · Novaciano
Params1.5B
Context128K
Q4_K_M1.0 GB
CodingReasoningRoleplay
LL
jknottllm/Meta-Llama-3-8B-Instruct-FineTuned
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
DeepHermes 3 Llama 3 3B Preview
Llama · ysn-rfd
Params3.21B
Context128K
Smallest1.9 GB
ReasoningRoleplayTool use
LL
llama3 13.45b Instruct
Llama · mradermacher
Params13.3B
Context8K
Q4_K_M8.1 GB
GGUF
ME
MedLlama-3-8B_DARE
Medllama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ST
Strawberrylemonade L3 70B v1.1
Strawberrylemonade · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Llama 3 8B Instruct Gadsby
Llama · sofuego
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Llama3 DiscoLeo Instruct 8B v0.1
Llama · cstr
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 instrucTrans Enko 8b
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Trendyol LLM 8b Chat v2.0
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 Med42 8B
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Tess 2.0 Llama 3 70B
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
llama3.1 airoboros3.2 QDT 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama3 merge biomed 8b
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
markrodrigo Llama 3.1 8B Instruct Spatial SQL 1.0
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
CodingTool use
LL
Llama 3 8B Web
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
ET
EtherealRainbow v0.3 8B
Etherealrainbow · l3utterfly
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 SuperNova Lite
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
GGUF
LL
rubra-ai/Meta-Llama-3-70B-Instruct
Llama · featherless-ai-quants
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Hermes 3 Llama 3.1 70B
Llama · Niansuh
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
LL
AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.5
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Models Rinna Llama 3 Youko 8b Instruct
Llama · MaziyarPanahi
Params8.03B
Context8K
Smallest5.6 GB
GGUF
HE
NousResearch_Hermes 4 405B
Hermes · lmstudio-community
Params406B
Context128K
Q4_K_M243.1 GB
ReasoningTool use
LL
Llama3 8b Math Sft
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ME
ChenWeiLi/Med-ChimeraLlama-3-8B_SHERP
Med · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3 8B Instruct FineTuned
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
flammenai/Mahou-1.3b-llama3-8B
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Genesist-8B-EarlyPrototype-0.4
Genesist · mradermacher
Params8.03B
Context16K
Q4_K_M4.9 GB
GGUF

Keep browsing