Title: Llama 3.3 70B Instruct %E2%80%94 llama-3-3-70b-instruct
Canonical: https://llmeu.com/en/models/llama-3-3-70b-instruct/
Markdown mirror: https://llmeu.com/en/models/llama-3-3-70b-instruct.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json
Provider: Meta
Licence: llama3.3
Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet
Sources: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct https://www.llama.com/llama3_3/license/

# Llama 3.3 70B Instruct

[Meta](/en/providers/meta/)

Last reviewed: 14 Oct 2026

## Sovereignty and hosting

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

## Summary

Llama 3.3 70B Instruct is the December 2024 refresh of Meta%E2%80%99s 70B instruct model, with a 128k-token context window and the same Llama 3.3 Community License terms as Llama 3.1. Meta positions it as an alternative to the larger Llama 3.1 405B for general assistant work. It is text-only and is the largest dense Llama checkpoint still in common self-hosted use.

## Specifications

- Provider
  Meta (US)
- Context window
  131k
- Parameters
  70.55B
- Modalities
  text
- License
  llama3.3 %C2%B7 [licence](https://www.llama.com/llama3_3/license/)
- Open weights
  yes
- Release date
  06 Dec 2024
- Tasks
  [Reasoning](/en/tasks/reasoning/), [Summarisation](/en/tasks/summarization/), [Multilingual support](/en/tasks/multilingual-support/), [Retrieval (RAG)](/en/tasks/rag/)

## Languages

**Strong:** en, de, fr, it, pt, es

**Adequate:** hi, th

#### Strong

- en
- de
- fr
- it
- pt
- es

#### Adequate

- hi
- th

Not verified: the provider has not documented this claim. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists.

## When to use it

#### Strengths

- 70B dense quality at a fraction of 405B serving cost
- 128k-token context window
- mature quantisation and serving support

#### Limits

- Llama 3.3 Community License with a 700M MAU threshold and acceptable-use policy
- text-only, no image input
- needs multiple accelerators at BF16

## Frequently asked questions

### Is Llama 3.3 70B Instruct served on LLM EU?

It has no endpoint in the catalogue, so it is catalogue only %E2%80%94 not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.

### Under what licence is Llama 3.3 70B Instruct released?

Llama 3.3 70B Instruct is recorded under llama3.3. The recorded licence text is https://www.llama.com/llama3_3/license/. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

### How large is Llama 3.3 70B Instruct, and what context window does it have?

Llama 3.3 70B Instruct is recorded at 70.55B (safetensors total 70,553,706,496) (source: https://huggingface.co/api/models/meta-llama/Llama-3.3-70B-Instruct), with a context window of 131072 tokens (source: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct).

### Pricing

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

### Verification status

Where a field has no source, the card shows it as unverified instead of filling it in. An empty field is information.

LLM EU Verified means documented, not legally certified. It is not an AI Act conformity assessment and LLM EU is not an EU body.

### Versions and variants

- catalogue %C2%B7 Catalogue only %C2%B7 [weights](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)

### Example request

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-3-3-70b-instruct","messages":[{"role":"user","content":"Hello"}]}'
```

No playground is deployed for this model: no endpoint serves it, so a request would have nowhere to go.

### Benchmarks

No published evaluation. This is a gap, not a hidden result.

### Sources

- [huggingface.co](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)
- [www.llama.com](https://www.llama.com/llama3_3/license/)

### Card changelog

- 06 Dec 2024 %E2%80%94 Release date
- 14 Oct 2026 %E2%80%94 Last reviewed

Last reviewed: 14 Oct 2026

### Tasks

- [Summarisation](/en/tasks/summarization/)