OSAIM
Open Source AI Models

Llama 3.1 405B Instruct

Meta's July 2024 flagship — the first open-weights model at 405B parameters. Trained on 15T tokens with 128K context. Rivals GPT-4o on many academic benchmarks and set the ceiling for open-weights quality for most of 2024. Running it self-hosted requires serious hardware (8× H100 at fp8 or multi-node at fp16); most users will run it via a hosted provider (Together, Groq, Fireworks). Llama 3.3 70B closed most of the practical gap at a fraction of the cost, so 405B is now most useful when 70B specifically hits its ceiling.

Parameters
405B
Context length
128K
Modality
text
Released
2024-07-23

Memory & hardware

VRAM (fp16)
810 GB
VRAM (Q4)
243 GB
Recommended
8× H100 80GB at fp8, or hosted via Together/Groq/Fireworks
Quantizations
fp16, fp8, q8_0, q4_k_m

License: Llama 3 Community License

SPDX
Commercial use
Yes
Modification
Yes
Redistribution
Yes

Benchmarks

HumanEval
89.0
IFEval
88.6
MMLU
87.3
ArenaHard
81.2
MATH
73.8
MMLU-Pro
73.3
GPQA
51.1
Benchmarks last verified 2026-07-02.

Hosted inference pricing

USD per million tokens.

ProviderInputOutput
together$3.50$3.50
groq$2.15$2.15
deepinfraCheapest$0.80$0.80
Pricing last verified 2026-07-02. Providers update rates frequently; confirm before integrating.

Run it yourself

Drop-in commands for the three most common open-source inference paths. The Ollama tag is a best-effort match against the registry; verify the size variant before pulling.

Run Llama 3.1 405B Instruct locally
Ollama (easiest)
ollama run llama3.1:405b
Single-line install + run; uses the official Ollama registry tag for this family.
vLLM (production)
vllm serve meta-llama/Llama-3.1-405B-Instruct
High-throughput hosted inference; one command to expose an OpenAI-compatible HTTP server.
Transformers (Python)
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-405B-Instruct")
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-405B-Instruct", device_map="auto", torch_dtype="auto"
)
Direct PyTorch usage. Pin a torch / cuda version that matches your GPU.
Hugging Face ID: meta-llama/Llama-3.1-405B-Instruct

Related models

Same family or similar size — useful when shopping around.

Llama 3.2 90B Vision
90B

Larger vision-language Llama variant, competitive with the proprietary multimodal frontier on standard image-understanding benchmarks. Drops in as a vision upgrade where 11B isn't sharp enough. Requires substantial GPU memory in fp16; most teams will run it quantized or on multi-GPU. A natural pairing with retrieval pipelines that fetch image-rich chunks alongside text.

Context
128K
License
llama-3
VRAM Q4
54 GB
Llama 3.3 70B Instruct
70B

Meta's December 2024 refresh of Llama 3 70B that closes most of the gap with Llama 3.1 405B for chat workloads while remaining tractable on a single H100. Strong instruction following, robust tool-use behaviour, and a 128K context window make it the default choice for production chat at 70B scale. The 3.3 release was trained on a refreshed instruction-tuning data mix and benefits from Meta's most recent alignment work. It outperforms the much larger 3.1 405B on several reasoning benchmarks at a fraction of inference cost. The licence is the Llama 3 Community License, which permits commercial use unless your service exceeds 700M monthly active users. Good pick for: production chat at scale, RAG over long documents, agentic workflows where tool use matters, and any 70B-tier replacement for closed proprietary models.

Context
128K
License
llama-3
VRAM Q4
42 GB
Llama 3.1 70B Instruct
70B

The pre-3.3 70B workhorse. Same base architecture as Llama 3.3 70B but the earlier instruction-tuning recipe. Still widely referenced as a baseline in papers and provider docs, and still the default 70B on some hosted providers.

Context
128K
License
llama-3
VRAM Q4
42 GB
Llama 2 70B Chat
70B

Flagship Llama 2 release. Fundamentally superseded by Llama 3 70B on every benchmark, but relevant historically: the model that made 'open-weights chat model at frontier scale' credible for enterprise workloads.

Context
4K
License
llama-2
VRAM Q4
42 GB
Jamba 1.5 Large
398B

Hybrid Mamba-Transformer-MoE model with native 256K context (effective beyond 140K). 94B active parameters out of 398B total. The state-space-model layers give it linear-time scaling with sequence length, making it interesting for very long contexts. Licensed under AI21's open model licence, which permits most commercial use.

Context
256K
License
jamba-open
VRAM Q4
238.8 GB
Nemotron-4 340B Instruct
340B

NVIDIA's reward-modelling research vehicle. Trained primarily to be a synthetic-data-generation specialist rather than a chat-first model. Useful for teams building instruction-tuning datasets at scale.

Context
4K
License
llama-3
VRAM Q4
204 GB