Llama GGUF models

30022 GGUF models in the Llama family, quantized by 7347 uploaders. Sizes run from 1M to 1020B parameters. The longest trained context is 102400K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LL
Meta Llama 3.1 8B Instruct
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · lmstudio-community
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama 4 Scout 17B 16E Instruct
Llama · bartowski
Params108B
Context10240K
Q4_K_M67.5 GB
GGUF
LL
Llama 2 7B Chat
Llama · TheBloke
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · MaziyarPanahi
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.3 70B Instruct
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.3 70B Instruct Abliterated
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · lmstudio-community
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Llama3.3 8B Instruct Thinking Heretic Uncensored Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
LL
Meta-Llama-3-70B-Instruct-abliterated-v3.5
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
GGUF
LL
CreativeWriter Llama3.2 3B
Llama · theprint
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
models--MaziyarPanahi--Llama-3-8B-Instruct-32k-v0.1
Llama · MaziyarPanahi
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Dorna2 Llama3.1 8B Instruct
Llama · aeranginkaman
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Models Meta Llama Llama 3.2 1B Instruct
Llama · MaziyarPanahi
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.61B
Context128K
Q4_K_M2.2 GB
GGUF
LL
Models Meta Llama Llama 3.2 3B Instruct
Llama · MaziyarPanahi
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LL
Dolphin 3.0 Llama 3.1 8B
Llama · dphn
Params8B
Context128K
Q4_K_M4.9 GB
CodingTool use
LL
chronicle narrator
Llama · GWsuryaYT
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
LL
Llama-3.2-1B-Instruct
Llama · unsloth
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · QuantFactory
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Hermes 3 Llama 3.1 8B
Llama · NousResearch
Params8B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
LL
models--MaziyarPanahi--Llama-3-8B-Instruct-64k
Llama · MaziyarPanahi
Params8B
Context63K
Q4_K_M4.9 GB
GGUF
LL
Models Meta Llama Llama 3.3 70B Instruct
Llama · MaziyarPanahi
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · hugging-quants
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Models Meta Llama Meta Llama 3.1 70B Instruct
Llama · MaziyarPanahi
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama-4-Scout-17B-16E-Instruct
Llama · unsloth
Params108B
Context10240K
Q4_K_M65.4 GB
Vision
LL
Models Meta Llama Meta Llama 3.1 8B Instruct
Llama · MaziyarPanahi
Params8B
Context128K
Q4_K_M4.9 GB
GGUF

About the Llama GGUF models

Llama is represented on ggufmodels.com by 30,022 GGUF models, quantized by 7,347 uploaders on Hugging Face. The most downloaded are Meta Llama 3.1 8B Instruct, Llama 3.2 3B Instruct and Llama-3.2-3B-Instruct. Parameter counts run from 1M to 1020B, and the longest trained context window is 102400K tokens.

A Q4_K_M file of a Llama model is between 0.0 to 245.7 GB, which is the quant most people start with. Most files come from mradermacher (8238), RichardErkhov (3423) and tensorblock (1093). The quants you will meet most often are Q4_K_M (21448), Q5_K_M (16056), Q2_K (15979) and Q8_0 (15312), where the number is how many models offer that quant.

Frequently asked questions

Which Llama GGUF should I download?

The most downloaded Llama GGUF here is Meta Llama 3.1 8B Instruct. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Llama model need?

Q4_K_M files of Llama models on this site range from 0.0 to 245.7 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Llama GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing