LLMs · Meta

Llama 3.1 405B Instruct

Name: Llama 3.1 405B Instruct
Author: Meta

Parameters: 406B
Architecture: Dense
Max context: 128K tokens
License: llama3.1
Released: 2024-07

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llama3.1:405b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from Meta, for fine-tuning, vLLM, Transformers.

huggingface.co/meta-llama/Llama-3.1-405B-Instruct (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

Official repo · GitHub

Reference code, inference scripts and docs from Meta. The weights themselves download from Hugging Face.

github.com/meta-llama/llama-models (opens in a new tab)

Meta’s official Llama repo: model cards, prompt formats and download tools.

git clone https://github.com/meta-llama/llama-models

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run Llama 3.1 405B Instruct

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 405.9B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	Ollama library	macOSWindowsLinux	llama.cpp, MLX	`ollama run llama3.1:405b`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Llama-3.1-405B-Instruct-8bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve meta-llama/Llama-3.1-405B-Instruct`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-405B-Instruct`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
GPT4All	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get GPT4All
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
exo	Server	MLX	macOSLinux	MLX	Get exo
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	162 GB	167 GB	180 GB	GGUF · part 1 of 9 (opens in a new tab)
`Q3_K_M`	Low	199 GB	204 GB	216 GB	GGUF (Q3_K_S) · part 1 of 9 (opens in a new tab)
`Q4_K_M`	Good	248 GB	252 GB	265 GB
`Q5_K_M`	High	288 GB	293 GB	306 GB
`Q6_K`	High	333 GB	338 GB	350 GB
`Q8_0`	Very high	430 GB	435 GB	448 GB
`F16`	Full	812 GB	817 GB	829 GB	Original weights (opens in a new tab)

Best hardware for Llama 3.1 405B Instruct

Quality	Hardware	Quant	Memory	Speed	Runs
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI350X	`Q4_K_M`	267 GB / 288 GB	20.8 tok/s	Runs welltight fit
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip	`Q3_K_M`	216 GB / 252 GB	27.8 tok/s	Runs welltight fit
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI325X	`Q3_K_M`	216 GB / 256 GB	20.2 tok/s	Runs well
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA B200	`Q2_K`	176 GB / 180 GB	39.7 tok/s	Runs welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI300X	`Q2_K`	177 GB / 192 GB	22.7 tok/s	Runs welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q2_K`	183 GB / 192 GB	3.5 tok/s	Slowtight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q2_K`	198 GB / 384 GB	3.5 tok/s	Slow
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (512 GB)	`Q4_K_M`	283 GB / 384 GB	3.1 tok/s	Slow
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (256 GB)	`Q2_K`	183 GB / 192 GB	5.1 tok/s	Slowtight fit
71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	AMD EPYC 7002 / 7003 series NAS (512 GB)	`Q6_K`	375 GB / 471 GB	0.2 tok/s	Very slow

Check it on your own hardware

Run it on a cluster

Devices that can’t run Llama 3.1 405B Instruct alone can run it together. These example clusters do:

Try it with your own devices

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.