Instructions to use litert-community/Llama-4-Scout-17B-16E-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/Llama-4-Scout-17B-16E-Instruct with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=litert-community/Llama-4-Scout-17B-16E-Instruct \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
You need to agree to the conditions to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
LLAMA 4 COMMUNITY LICENSE AGREEMENT
Llama 4 Version Effective Date: April 5, 2025
"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation accompanying Llama 4 distributed by Meta at https://www.llama.com/docs/overview.
"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
"Llama 4" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads.
"Llama Materials" means, collectively, Meta’s proprietary Llama 4 and Documentation (and any portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking "I Accept" below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display "Built with Llama" on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include "Llama" at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a "Notice" text file distributed as a part of such copies: "Llama 4 is licensed under the Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved."
iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://www.llama.com/llama4/use-policy), which is hereby incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 4 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use "Llama" (the "Mark") solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 4 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
Llama 4 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Llama 4. If you access or use Llama 4, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at https://www.llama.com/llama4/use-policy.
Prohibited Uses
We want everyone to use Llama 4 safely and responsibly. You agree you will not use, or allow others to use, Llama 4 to:
Violate the law or others’ rights, including to:
Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
- Violence or terrorism
- Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
- Human trafficking, exploitation, and sexual violence
- The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
- Sexual solicitation
- Any other criminal activity
Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 4 related to the following:
Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
Guns and illegal weapons (including weapon development)
Illegal drugs and regulated/controlled substances
Operation of critical infrastructure, transportation technologies, or heavy machinery
Self-harm or harm to others, including suicide, cutting, and eating disorders
Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
Intentionally deceive or mislead others, including use of Llama 4 related to the following:
Generating, promoting, or furthering fraud or the creation or promotion of disinformation
Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
Generating, promoting, or further distributing spam
Impersonating another individual without consent, authorization, or legal right
Representing that the use of Llama 4 or outputs are human generated
Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
Fail to appropriately disclose to end users any known dangers of your AI system
Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 4
With respect to any multimodal models included in Llama 4, the rights granted under Section 1(a) of the Llama 4 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
- Reporting issues with the model: https://github.com/meta-llama/llama-models/issues
- Reporting risky content generated by the model: developers.facebook.com/llama_output_feedback
- Reporting bugs and security concerns: facebook.com/whitehat/info
- Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 4: LlamaUseReport@meta.com
Log in or Sign Up to review the conditions and access this model content.
Llama-4-Scout-17B-16E-Instruct LiteRT-LM
Built with Llama.
This repository is a conversion of the text decoder of meta-llama/Llama-4-Scout-17B-16E-Instruct to LiteRT-LM, for the GPU of a desktop Mac: on an Apple M4 Max (128 GB) the file decodes 19.79 tok/s and prefills 217.23 tok/s on the GPU (WebGPU), with LiteRT-LM built from source (main 02d7e8d8), measured on 2026-11-18. Speed still being tuned (updates follow).
Run it on the GPU, in a directory that holds that build (build the runtime) and the file:
mkdir -p cache
./litert_lm_advanced_main --backend=gpu --model_path=llama4_scout_17b_16e_instruct_int4_ekv4096.litertlm \
--max_output_tokens=2048 --min_log_severity=2 --sampler_top_k=1 \
--sampler_handles_input=false --cache_dir=cache --input_prompt="What is 17 + 25? Answer briefly."
Run here as printed on 2026-11-21, it answered "42.": the first run took 109 s and wrote a 62.5 GB weight cache into cache, the second took 19 s.
When it does not work:
- LiteRT-LM 0.19.2, the latest release on PyPI on 2026-11-18, does not run this conversion, and neither does 0.19.1 (checked with a 4-layer slice that uses the same SiLU
moeop): theirmoekernels reject SiLU, the activation of this model's experts. SiLU is in two open LiteRT pull requests, #11192 and #11188 (build the runtime). - A GPU run needs about 68 GB of memory, and the cache needs 62.5 GB of disk. Every run reads the cache as mapped file pages next to a process footprint of about 5.6 GB. When the cache does not fit in memory, the run stalls without an error: started with 53 GB reclaimable, a benchmark run finished no iteration in 28 minutes; its log matched a finished run's log up to where that run went on to print its results, and nothing came after that (memory).
- Use the GPU, not the CPU: on the CPU the file picks the source model's top token at 21 of 24 checked positions, and the check passes from 22 (accuracy).
- Do not switch the GPU to fp16 activations (the file declares fp32): with fp16, 23 of the 24 checked positions came back as all-zero logits, with no error.
Files
| File | Backend | Quantization | Context | Size |
|---|---|---|---|---|
llama4_scout_17b_16e_instruct_int4_ekv4096.litertlm |
GPU (WebGPU) | the 16 experts of every layer int4 (blocks of 128); the attention and shared-expert linear layers, the token table and the output layer int8 (per channel); the routers fp32 | 4096 | 62.57 GB |
All 48 layers of the text decoder. The vision tower and the projector of the source are not converted (0.80 % of its parameters), so the file takes text only (conversion notes).
Performance
| File | Backend | Prefill (tok/s) | Decode (tok/s) | Time to first token | Peak footprint |
|---|---|---|---|---|---|
llama4_scout_17b_16e_instruct_int4_ekv4096.litertlm |
GPU (WebGPU) | 217.23 | 19.79 | 4.8 s | 5.6 GB + the 62.5 GB cache |
Apple M4 Max (128 GB), 1,024 prefill and 256 decode tokens, context 2,048, measured on 2026-11-18 with the weight cache already written (how it was measured).
Accuracy
| File | Backend | Same verdict as the source model | Ends with the stop token | 3 turns |
|---|---|---|---|---|
llama4_scout_17b_16e_instruct_int4_ekv4096.litertlm |
GPU (WebGPU) | 12 / 12 | 12 / 12 | pass |
12 questions and a 3-turn conversation, greedy, judged against the source model's bf16 weights computed in fp32 with Transformers' modules. 7 of the 12 answers are the source model's answer token for token; in the other 5 the wording differs, twice with a stray word ("There are impeccable 7 days in a week." where the source model writes "There are 7 days in a week.") (questions and method).
On the CPU, LiteRT-LM quantizes the inputs of int8 linear layers to int8 at run time (XNNPACK qd8); the GPU does not. With this file the CPU leaves the source model at 3 of the 24 checked positions, the same 3 in each of 3 processes, so the CPU is not a supported backend of this file. How much of that this run-time quantization explains was not separated at 48 layers.
How it was converted
- The
moeoutput has a second consumer in the graph, so the GPU does not fuse the residual add into themoekernel; fused, the shader does not parse and the logits are wrong. - The op's
top_weightsinput is computed in the graph: with a constant there, the WebGPU process aborts while the engine is built. - The token table and the output layer are int8 per channel, one constant of about 1 GB each.
- The chat template in the file is rewritten from the source's for LiteRT-LM's template engine, which reads
is not noneas "is defined" and whosetojsontakes noindentargument (chat template).
Limitations
- Text only: images are not an input of this file.
- Context 4096 tokens. The graph computes the source's attention for positions 0 to 8190 only, and the file stays inside that range.
- Measured on a desktop only (Apple M4 Max, 128 GB): the 62.57 GB file does not fit in a phone's memory, and Android, iOS and Macs with less memory were not tried.
- Tool calls come back as reply text: the file declares LiteRT-LM's generic model type. Tool calling was not run with this file (chat template).
License
Llama 4 Community License, the license of meta-llama/Llama-4-Scout-17B-16E-Instruct. This repository carries the agreement (LICENSE), the Llama 4 Acceptable Use Policy (USE_POLICY.md) and NOTICE.
From the Acceptable Use Policy: "With respect to any multimodal models included in Llama 4, the rights granted under Section 1(a) of the Llama 4 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models."
- Downloads last month
- 1
Model tree for litert-community/Llama-4-Scout-17B-16E-Instruct
Base model
meta-llama/Llama-4-Scout-17B-16E