Llama GGUF models

30050 GGUF models in the Llama family, quantized by 7365 uploaders. Sizes run from 1M to 1020B parameters. The longest trained context is 102400K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LL
Thespis Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay
LL
Llama 3 8b 64k PoSE
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Unichat llama3 Chinese 8B
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama-3-sqlcoder-8b
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
LL
Colossal LLaMA 2 13b Base
Llama · mradermacher
Params13.4B
Context4K
Q4_K_M8.1 GB
GGUF
LL
VeriPrefer CodeLlama 7b
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
LL
Llama 3.1 Tulu 3 70B
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.1 8B Lexi Uncensored V2 Heretic
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Dracarys Llama 3.1 70B Instruct
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.1 8B Instruct RoleVerse SFT DPO
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
LL
Einstein-v6.1-Llama3-8B
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
Tool use
LL
Llama-3-Swallow-8B-Instruct-v0.1
Llama · mmnga
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Configurable Llama 3 8B v0.3
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama3-8B-DarkIdol-1.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
LL
Llama 3.1 8B ascii cats
Llama · Needless64
Params3.2B
Context128K
Smallest3.4 GB
GGUF
LL
AMD Llama 135m code i1
Llama · mradermacher
Params134M
Context2K
Q4_K_M0.1 GB
Coding
LL
Hermes 3 Llama 3.1 8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
LL
Llama 4 Scout 17B 16E Instruct Abliterated v2
Llama · mradermacher
Params108B
Context10240K
Smallest22.2 GB
GGUF
LL
Llama3.1_StoryGeneration
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-8B-Magpie-Align-v0.1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B ProLong 64k Base
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Swallow 70B v0.1
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Esper 70b
Llama · mradermacher
Params69B
Context4K
Q4_K_M42.3 GB
Coding
LL
Rawr_Llama3_8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
SOVL-MopeyMule-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.3 MagicalGirl 2.5 i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.1 CyberAlpha8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
LLaMA 2 7B 32K Instruct
Llama · rozek
Params6.74B
Context32K
Q4_K_M4.1 GB
GGUF
LL
Polypsyche Llama 3.1 8B Instruct Agent 0.003 128K code ds auto Logic i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingTool use
LL
New Dawn Ultra Llama 3 70B 32K v1.0
Llama · mradermacher
Params70.6B
Context32K
Q4_K_M42.5 GB
GGUF

Keep browsing