Skip to content
Local AI Wizard
Your machine
Theme

Llama-3.1-405B-Instruct

meta-llama · meta-llama/Llama-3.1-405B-Instruct

Weights license: Publisher terms: Llama 3.1 · code and components may use other terms

Reported by the publisher24 resultsmeta-llama's model card · read 2026-10-25 · not ranked · see them
Memory needed~305 GBQ4 weights + working room, before the machine's reserve
Parameters405.9 BHub safetensors total
Repository updated2024-09-25A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

24 results · meta-llama's model card · read 2026-10-25
MMLU
87.3Llama 3.1 405B Instruct · Instruction tuned models · General
MMLU (CoT)
88.6Llama 3.1 405B Instruct · Instruction tuned models · General
MMLU-Pro (CoT)
73.3Llama 3.1 405B Instruct · Instruction tuned models · General
IFEval
88.6Llama 3.1 405B Instruct · Instruction tuned models · General
ARC-C
96.9Llama 3.1 405B Instruct · Instruction tuned models · Reasoning
GPQA
50.7Llama 3.1 405B Instruct · Instruction tuned models · Reasoning
HumanEval
89.0Llama 3.1 405B Instruct · Instruction tuned models · Code
MBPP ++ base version
88.6Llama 3.1 405B Instruct · Instruction tuned models · Code
Every reported result24
Multipl-E HumanEval
75.2Llama 3.1 405B Instruct · Instruction tuned models · Code
Multipl-E MBPP
65.7Llama 3.1 405B Instruct · Instruction tuned models · Code
GSM-8K (CoT)
96.8Llama 3.1 405B Instruct · Instruction tuned models · Math
MATH (CoT)
73.8Llama 3.1 405B Instruct · Instruction tuned models · Math
API-Bank
92.0Llama 3.1 405B Instruct · Instruction tuned models · Tool Use
BFCL
88.5Llama 3.1 405B Instruct · Instruction tuned models · Tool Use
Gorilla Benchmark API Bench
35.3Llama 3.1 405B Instruct · Instruction tuned models · Tool Use
Nexus (0-shot)
58.7Llama 3.1 405B Instruct · Instruction tuned models · Tool Use · 0-shot
Multilingual MGSM (CoT)
91.6Llama 3.1 405B Instruct · Instruction tuned models · Multilingual
MMLU · Portuguese (5-shot, macro_avg/acc)
84.95Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · Spanish (5-shot, macro_avg/acc)
85.08Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · Italian (5-shot, macro_avg/acc)
85.04Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · German (5-shot, macro_avg/acc)
84.36Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · French (5-shot, macro_avg/acc)
84.66Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · Hindi (5-shot, macro_avg/acc)
80.31Llama 3.1 405B · Multilingual benchmarks · General · 5-shot
MMLU · Thai (5-shot, macro_avg/acc)
78.21Llama 3.1 405B · Multilingual benchmarks · General · 5-shot

Values as printed on the card, with the publisher's own settings (card section: Benchmark scores › Instruction tuned models; Benchmark scores › Instruction tuned models › Multilingual benchmarks). Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 1

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

One memory tier short 1

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
text-generation
Architecture
LlamaForCausalLM
Library in source
transformers
Weight license
Publisher terms: Llama 3.1
Commercial use
Allowed with conditions Over 700M monthly users needs a Meta license; show "Built with Llama" · Llama 3.1 Community License (meta-llama/llama-models) · read 2026-10-18license text
Every stored field13 fields
Revision checked
be673f326cab4cd22ccfef76109faf68e41aa5f1
Architecture
LlamaForCausalLM
Library
transformers
Hub task tag
text-generation
Declared base models
meta-llama/Meta-Llama-3.1-405B
Formats
safetensors, pt
Access
Gated (manual)
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 405.85B · BF16checked 2026-09-26
Repository created
2024-07-16creation is not the model's release
Repository updated
2024-09-25a commit is not a release date
Hub downloads (30 days) · likes
9,375 · 605this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.