Llama-3.3-70B-Instruct
Version: 9
Direct from Azure models
Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:- Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
- Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
- Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
- Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.
Key capabilities
About this model
The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.Key model capabilities
| Category | Benchmark | # Shots | Metric | Llama 3.1 8B Instruct | Llama 3.1 70B Instruct | Llama-3.3 70B Instruct | Llama 3.1 405B Instruct |
|---|---|---|---|---|---|---|---|
| MMLU (CoT) | 0 | macro_avg/acc | 73.0 | 86.0 | 86.0 | 88.6 | |
| MMLU Pro (CoT) | 5 | macro_avg/acc | 48.3 | 66.4 | 68.9 | 73.3 | |
| Steerability | IFEval | 80.4 | 87.5 | 92.1 | 88.6 | ||
| Reasoning | GPQA Diamond (CoT) | 0 | acc | 31.8 | 48.0 | 50.5 | 49.0 |
| Code | HumanEval | 0 | pass@1 | 72.6 | 80.5 | 88.4 | 89.0 |
| MBPP EvalPlus (base) | 0 | pass@1 | 72.8 | 86.0 | 87.6 | 88.6 | |
| Math | MATH (CoT) | 0 | sympy_intersection_score | 51.9 | 68.0 | 77.0 | 73.8 |
| Tool Use | BFCL v2 | 0 | overall_ast_summary/macro_avg/valid | 65.4 | 77.5 | 77.3 | 81.1 |
| Multilingual | MGSM | 0 | em | 68.9 | 86.9 | 91.1 | 91.6 |
Use cases
See Responsible AI for additional considerations for responsible use.Key use cases
Llama 3.3 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.3 model also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.3 Community License allows for these use cases.Out of scope use cases
Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.3 Community License. Use in languages beyond those explicitly referenced as supported in this model card**. **Note: Llama 3.3 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.3 models for languages beyond the 8 supported languages provided they comply with the Llama 3.3 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.3 in additional languages is done in a safe and responsible manner.Pricing
Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.Technical specs
Llama 3.3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.Training cut-off date
December 2023Training time
Training utilized a cumulative of 39.3M GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.| Training Time (GPU hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) | |
|---|---|---|---|---|
| Llama 3.3 70B | 7.0M | 700 | 2,040 | 0 |
Input formats
Multilingual TextOutput formats
Multilingual Text and codeSupported languages
Llama 3.3 supports 7 languages in addition to English: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Llama may be able to output text in other languages than those that meet performance thresholds for safety and helpfulness.Sample JSON response
The provider has not supplied this information.Model architecture
Llama 3.3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.| Training Data | Params | Input modalities | Output modalities | Context length | GQA | Token count | Knowledge cutoff | |
|---|---|---|---|---|---|---|---|---|
| Llama 3.3 (text only) | A new mix of publicly available online data. | 70B | Multilingual Text | Multilingual Text and code | 128k | Yes | 15T+* | December 2023 |
Long context
128kOptimizing model performance
The provider has not supplied this information.Additional assets
Instructions on how to provide feedback or comments on the model can be found in the model README . For more technical information about generation parameters and recipes for how to use Llama 3.3 in applications, please go here .Training disclosure
Training, testing and validation
Llama 3.3 was pretrained on ~15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 25M synthetically generated examples.Distribution
Distribution channels
The provider has not supplied this information.More information
The provider has not supplied this information.Responsible AI considerations
Safety techniques
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:- Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.
- Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
- Provide protections for the community to help prevent the misuse of our models.
As part of our responsible release approach, we provide the community with safeguards that developers should deploy with Llama models or other LLMs, including Llama Guard 3, Prompt Guard and Code Shield. All our reference implementations demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box. Note that this release introduces new capabilities, including a longer context window, multilingual inputs and outputs and possible integrations by developers with third party tools. Building with these new capabilities requires specific considerations in addition to the best practices that generally apply across all Generative AI use cases. Tool-use: Just like in standard software development, developers are responsible for the integration of the LLM with the tools and services of their choice. They should define a clear policy for their use case and assess the integrity of the third party services they use to be aware of the safety and security limitations when using this capability. Refer to the Responsible Use Guide for best practices on the safe deployment of the third party safeguards. Multilinguality: Llama 3.3 supports 7 languages in addition to English: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Llama may be able to output text in other languages than those that meet performance thresholds for safety and helpfulness. We strongly discourage developers from using this model to converse in non-supported languages without implementing finetuning and system controls in alignment with their policies and the best practices shared in the Responsible Use Guide.
Safety evaluations
We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, coding assistant, tool calls. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application.Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, tools calls, coding or memorization. For both scenarios, we conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets.
We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets. We specifically focused our efforts on mitigating the following critical risk areas: 1- CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) helpfulness
To assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of the Llama 3.3 model could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. 2. Child Safety Child Safety risk assessments were conducted using a team of experts, to assess the model's capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences. 3. Cyber attack enablement
Our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention.
Known limitations
The core values of Llama 3.3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. But Llama 3.3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.3's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.3 model, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our Responsible Use Guide , Trust and Safety solutions, and other resources to learn more about responsible development.Acceptable use
Acceptable use policy
Intended Use Cases Llama 3.3 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.3 model also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.3 Community License allows for these use cases. Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.3 Community License. Use in languages beyond those explicitly referenced as supported in this model card**. **Note: Llama 3.3 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.3 models for languages beyond the 8 supported languages provided they comply with the Llama 3.3 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.3 in additional languages is done in a safe and responsible manner.Quality and performance evaluations
Source: Meta In this section, we report the results for Llama 3.3 relative to our previous models.Instruction tuned models
| Category | Benchmark | # Shots | Metric | Llama 3.1 8B Instruct | Llama 3.1 70B Instruct | Llama-3.3 70B Instruct | Llama 3.1 405B Instruct |
|---|---|---|---|---|---|---|---|
| MMLU (CoT) | 0 | macro_avg/acc | 73.0 | 86.0 | 86.0 | 88.6 | |
| MMLU Pro (CoT) | 5 | macro_avg/acc | 48.3 | 66.4 | 68.9 | 73.3 | |
| Steerability | IFEval | 80.4 | 87.5 | 92.1 | 88.6 | ||
| Reasoning | GPQA Diamond (CoT) | 0 | acc | 31.8 | 48.0 | 50.5 | 49.0 |
| Code | HumanEval | 0 | pass@1 | 72.6 | 80.5 | 88.4 | 89.0 |
| MBPP EvalPlus (base) | 0 | pass@1 | 72.8 | 86.0 | 87.6 | 88.6 | |
| Math | MATH (CoT) | 0 | sympy_intersection_score | 51.9 | 68.0 | 77.0 | 73.8 |
| Tool Use | BFCL v2 | 0 | overall_ast_summary/macro_avg/valid | 65.4 | 77.5 | 77.3 | 81.1 |
| Multilingual | MGSM | 0 | em | 68.9 | 86.9 | 91.1 | 91.6 |
Benchmarking methodology
Source: Meta We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, coding assistant, tool calls. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application. Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, tools calls, coding or memorization. Red teamingFor both scenarios, we conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets.
We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets. . We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations.
Public data summary
Source: Meta The provider has not supplied this information.Model Specifications
Context Length128000
Quality Index0.74
LicenseCustom
Training DataDecember 2023
Last UpdatedDecember 2025
Input TypeText
Output TypeText
ProviderMeta
Languages8 Languages
Related Models
