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
Llama · yh-yao
Params8.03B
Context8K
Smallest4.0 GB
GGUF
LL
Turkish Llama 8b Instruct v0.1
Llama · matrixportalx
Params8.03B
Context8K
Smallest5.7 GB
GGUF
LL
lora Meta Llama 3 8B Instruct
Llama · weber50432
Params8.03B
Context8K
Smallest16.1 GB
GGUF
LL
Llama 3 8B Web Q4 K M
Llama · itlwas
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Defne llama3 2x8B
Llama · tensorblock
Params13.7B
Context8K
Smallest5.2 GB
GGUF
LL
New Dawn Llama3 70b 32K v1.0
Llama · NexesQuants
Params70.6B
Context32K
Smallest48.1 GB
GGUF
LL
llama 3 40 percent compression Q4 K M
Llama · PruningEverything
Params4.79B
Context8K
Q4_K_M4.2 GB
GGUF
LL
Llama 3 Taiwan 70B Instruct Rc3
Llama · tensorblock
Params70.6B
Context8K
Smallest26.4 GB
GGUF
LL
llama 3 8b lora law2entity
Llama · rubenamtz0
Params8B
Context—
Smallest0.0 GB
GGUF
VA
Value4AI ValueLlama 3 8B
Valuellama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
Llama3 DiscoLeo Instruct 8B 32k v0.1 Q5 K S
Llama · jott1970
Params8.03B
Context64K
Smallest5.6 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · FusionQuill
Params8.03B
Context63K
Q4_K_M4.9 GB
GGUF
LL
Meta-Llama-3-8B-Instruct
Llama · joshnader
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 ArrowSE 8B v0.1
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta-Llama-3-8B-Instruct
Llama · modularai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Instruct Finance RAG
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
new dim
Llama · splendidcomputer
Params8.03B
Context8K
Smallest4.7 GB
GGUF
SU
tsavage68 Summary L3 1000steps 1e7rate SFT2
Summary · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
LL
llama 3 30 percent compression Q4 K M
Llama · PruningEverything
Params5.63B
Context8K
Q4_K_M3.5 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · aswinaus
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · Georgia47
Params8.03B
Context8K
Smallest9.3 GB
GGUF
LL
llama3 discolm orca
Llama · cstr
Params8.03B
Context8K
Smallest4.9 GB
GGUF
AE
L3-Aethora-15B
Aethora · NikolayKozloff
Params15B
Context8K
Smallest8.6 GB
GGUF
LL
Llama3-8B-SFT-code_bagel-bnb-4bit
Llama · rombodawg
Params8.03B
Context8K
Smallest8.5 GB
Coding
LL
Llama3 German 8B
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
CH
ChaoticSoliloquy 4x8B
Chaoticsoliloquy · xxx777xxxASD
Params24.9B
Context8K
Smallest13.0 GB
GGUF
LL
Llama 3 Translation 8B v0.180 Q5 K M
Llama · DarkClaw42
Params8.17B
Context8K
Smallest5.8 GB
GGUF
LL
llama3.1 8b spaetzle v74 Q4 K M
Llama · jott1970
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3 Instruct Abliteration LoRA 8B
Llama · dimvasilk
Params88M
Context—
Smallest0.4 GB
GGUF
LL
Llama 3 8B ProLong 64k Instruct
Llama · DevQuasar-3
Params8.03B
Context64K
Q4_K_M4.9 GB
GGUF

Keep browsing