GGUF models: llama2 license

2213 GGUF models listed under the llama2 license on Hugging Face. Always read the license text before commercial use. Sizes run from 41M to 240B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
XU
XuanYuan 70B Chat
Xuanyuan · mradermacher
Params69.1B
Context8K
Q4_K_M41.9 GB
GGUF
LL
bunnycore Blackbird Llama 3 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
NS
nsfwthrowitaway69 Venus 120b v1.2
Nsfwthrowitaway · RichardErkhov
Params120B
Context4K
Smallest44.2 GB
GGUF
VI
vinallama 7b chat
Vinallama · vilm
Params6.86B
Context4K
Smallest4.7 GB
GGUF
LL
Llama 2 7b Chat Hf
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
SA
SambaLingo Thai Chat
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
LL
LlamaGuard 7b
Llama · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
LL
Uukuguy Speechless Codellama Dolphin Orca Platypus 13b
Llama · tensorblock
Params13B
Context16K
Smallest4.9 GB
Coding
LL
ELYZA Japanese Llama 2 7b
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
LL
Llama 2 7b Chat Hf
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
GO
HiTZ GoLLIE 34B
Gollie · tensorblock
Params33.7B
Context16K
Smallest12.5 GB
Coding
LL
Llama 2 7b spin rephrased 10k
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
XU
XuanYuan 13B
Xuanyuan · mradermacher
Params13.1B
Context8K
Q4_K_M7.9 GB
GGUF
PU
PULI LlumiX 32K
Puli · tensorblock
Params6.74B
Context32K
Smallest2.5 GB
GGUF
LM
Yhyu13/LMCocktail-10.7B-v1
Lmcocktail · featherless-ai-quants
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
CO
Danielbrdz CodeBarcenas 7b
Codebarcenas · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
GGUF
LL
llama 2 13b FINETUNE5 4w r4 q k v o
Llama · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
VI
Vicuna Mmlu Val Only Correct Mcq 7b Ep2
Vicuna · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
PS
neverending text balanced
Psyfighter · MRA-Labs
Params13B
Context4K
Smallest9.5 GB
Roleplay
XW
Xwinter 120b
Xwinter · bcse
Params118B
Context4K
Smallest43.2 GB
GGUF
LL
llama 3 open hermes disco
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
VE
Venus 120b v1.2 i1
Venus · mradermacher
Params120B
Context4K
Smallest25.6 GB
GGUF
LL
Llama 3 Smaug 8B
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
VI
vicuna class student all hal 7b
Vicuna · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
LL
layer wise lora llava 1.5 7B scienceqa 1epoch GGUF Q4 K M
LLaVA · c2d-usp
Params6.74B
Context4K
Q4_K_M4.1 GB
Vision
LL
llama2 chat koalpaca
Llama · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
GGUF
ST
Stheno-Mix-L2-20B
Stheno · mradermacher
Params20.6B
Context4K
Q4_K_M12.4 GB
GGUF
AI
Airoboros C34B 2.1
Airoboros · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
GGUF
LL
CodeLlama 7b Hf
Llama · stacklok
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
MY
MysticFusion 13B
Mysticfusion · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF

Keep browsing