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
LL
Codellama CodeLlama 70b Python Hf
Llama · tensorblock
Params69B
Context4K
Smallest25.5 GB
Coding
TO
Llm Agents Tora Code 7b v1.0
Tora · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Coding
SA
SambaLingo Serbian Base
Sambalingo · mradermacher
Params6.95B
Context4K
Q4_K_M4.2 GB
GGUF
LL
Opencsg codeLlama 7b v0.2
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
OP
Openthaigpt 1.0.0 70b Chat
Openthaigpt · mradermacher
Params69.1B
Context2K
Q4_K_M41.5 GB
GGUF
LL
birgermoell/llama-3-open-hermes-disco
Llama · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
TE
test gguf modified
Test · rarad
Params620M
Context32K
Smallest0.3 GB
GGUF
LE
LeetCodeWizard 13B V1.1a
Leetcodewizard · Nan-Do
Params13B
Context16K
Smallest6.3 GB
Coding
AI
Airavata
Airavata · ai4bharat
Params6.87B
Context4K
Smallest13.7 GB
GGUF
LL
TheBloke CodeLlama 13B Instruct Fp16
Llama · tensorblock
Params13B
Context16K
Smallest4.9 GB
Coding
LL
Llama 2 7b Chat Hf
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
AU
Augmental 13b v1.50 B
Augmental · Heralax
Params13B
Context4K
Smallest9.2 GB
GGUF
XW
Xwin LM 70B V0.1
Xwin · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
LL
Taiwan LLaMa v1.0
Llama · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
Vicuna 13b v1.5
Vicuna · QuantFactory
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
CO
Code Millenials 13b
Code · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
Coding
AD
ADELIE SFT 3B
Adelie · mradermacher
Params3.61B
Context128K
Q4_K_M2.2 GB
GGUF
LL
OpenMath CodeLlama 7b Python Hf
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
VE
Venus 103b v1.1 i1
Venus · mradermacher
Params103B
Context4K
Smallest22.0 GB
GGUF
DE
Deepreneur blue lizard
Deepreneur · mmnga
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
bangla llama 7b base v0.1
Llama · mradermacher
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
LL
ELYZA-japanese-Llama-2-7b-fast
Llama · opparco
Params6.85B
Context4K
Q4_K_M4.2 GB
GGUF
XW
Xwin LM 7B V0.2
Xwin · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
sanghwa-na/llama2-13b.kor
Llama · featherless-ai-quants
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
GO
Goliath-longLORA-120b-rope8-32k-fp16
Goliath · bartowski
Params118B
Context4K
Q4_K_M70.6 GB
GGUF
CH
Changgil/k2s3_test_24001
Changgil · featherless-ai-quants
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
LL
Llama 2 7B Chat
Llama · SergeUSS
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Llama Polyglot 13b
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
WE
webbigdata ALMA 7B Ja V2
Webbigdata · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
DI
DiscoLM 120b
Discolm · TheBloke
Params118B
Context4K
Smallest49.6 GB
Tool use

Keep browsing