Skip to content
Weights Not Walls
Menu

meta-llama

Llama-3.1-405B

Reviewedgated on the Hub
Size
406B parameterscounted from the safetensors header on the Hub
Licence
unknown, Llama 3.1 Community License AgreementOur reading, check the licence: Commercial use is allowed unless your products had more than 700 million monthly active users in the calendar month before the Llama 3.1 release date, in which case you need a licence from Meta. If you distribute it, or a product or service containing it, you must include the agreement and display "Built with Llama", and any AI model built with Llama or its outputs must start its name with "Llama" (unlike Llama 3, there is no ban on using outputs to improve other models). The Acceptable Use Policy is part of the licence but is a separate document, not in this text.
On the Hub since
16 Jul 2024the date the repo was created
Context length
Not known
Kind
Base model (no base model declared on the Hub)LlamaForCausalLM
On Hugging Face
meta-llama/Llama-3.1-405B46k downloads in the last 30 days, 998 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 7.9 GB, worked out from the model's config (RedHatAI/Meta-Llama-3.1-405B-FP8), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF (converted by ThomasBaruzier), 4.7k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ3_XXS145.1 GBfile size, 4 parts153.5 GB145.1 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ3_XXS
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ3_XXS/Meta-Llama-3.1-405B-Instruct-IQ3_XXS-*-of-00004.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
IQ3_XS154.7 GBfile size, 4 parts163.0 GB154.7 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ3_XS
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ3_XS/Meta-Llama-3.1-405B-Instruct-IQ3_XS-*-of-00004.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
Q3_K_S163.2 GBfile size, 4 parts171.6 GB163.2 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:Q3_K_S
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-Q3_K_S/Meta-Llama-3.1-405B-Instruct-Q3_K_S-*-of-00004.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
IQ3_S163.5 GBfile size, 4 parts171.8 GB163.5 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ3_S
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ3_S/Meta-Llama-3.1-405B-Instruct-IQ3_S-*-of-00004.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
IQ3_M169.3 GBfile size, 4 parts177.6 GB169.3 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ3_M
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ3_M/Meta-Llama-3.1-405B-Instruct-IQ3_M-*-of-00004.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
Q3_K_M182.0 GBfile size, 5 parts190.3 GB182.0 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:Q3_K_M
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-Q3_K_M/Meta-Llama-3.1-405B-Instruct-Q3_K_M-*-of-00005.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
Q3_K_L198.2 GBfile size, 5 parts206.6 GB198.2 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:Q3_K_L
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-Q3_K_L/Meta-Llama-3.1-405B-Instruct-Q3_K_L-*-of-00005.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
IQ4_XS201.7 GBfile size, 5 parts210.1 GB201.7 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ4_XS
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ4_XS/Meta-Llama-3.1-405B-Instruct-IQ4_XS-*-of-00005.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
IQ4_NL213.4 GBfile size, 5 parts221.8 GB213.4 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:IQ4_NL
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-IQ4_NL/Meta-Llama-3.1-405B-Instruct-IQ4_NL-*-of-00005.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
Q4_K_S214.7 GBfile size, 5 parts223.0 GB214.7 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:Q4_K_S
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-Q4_K_S/Meta-Llama-3.1-405B-Instruct-Q4_K_S-*-of-00005.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
Q4_K_M226.4 GBfile size, 6 parts234.8 GB226.4 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:Q4_K_M
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-Q4_K_M/Meta-Llama-3.1-405B-Instruct-Q4_K_M-*-of-00006.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF
F16756.0 GBfile size, 18 parts764.4 GB756.0 + 7.9 + 0.50
Commands
llama.cpp
llama-server -hf ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF:F16
Download
hf download ThomasBaruzier/Meta-Llama-3.1-405B-Instruct-GGUF --include "Meta-Llama-3.1-405B-Instruct-F16/Meta-Llama-3.1-405B-Instruct-F16-*-of-00018.gguf" --local-dir Meta-Llama-3.1-405B-Instruct-GGUF

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights756.0 GBfile size764.3 GB756.0 + 7.9 + 0.50
hf download meta-llama/Llama-3.1-405B --local-dir Llama-3.1-405B
Other conversions (6; sizes not read)

The Hub tags 12 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.