mradermacher/Cosmos-Reason2-8B-i1-GGUF

---

base_model: nvidia/Cosmos-Reason2-8B extragatedbutton_content: Submit extragatedfields: ? By clicking Submit below, I accept the terms of the NVIDIA Open Model License Agreement and acknowledge that I am an adult of legal age of majority in the country in which the Cosmos Models will be used and have authority to accept this Agreement : checkbox extragatedprompt: "# NVIDIA Open Model License Agreement\nVersion Release Date: September 23, 2025\nThis NVIDIA Open Model License Agreement (the “Agreement”) is a legal agreement between the Legal Entity You represent, or if no entity is identified, You and NVIDIA Corporation and its Affiliates (“NVIDIA”) and governs Your use of the Models that NVIDIA provides to You under this Agreement. NVIDIA and You are each a “party” and collectively the “parties.” \nNVIDIA models released under this Agreement are intended to be used permissively and enable the further development of AI technologies. Subject to the terms of this Agreement, NVIDIA confirms that: \n- Models are commercially usable. - You are free to create and distribute Derivative Models. - NVIDIA does not claim ownership to any outputs generated using the Models or Model Derivatives. \nBy using, reproducing, modifying, distributing, performing or displaying any portion or element of the Model or Derivative Model, or otherwise accepting the terms of this Agreement, you agree to be bound by this Agreement. \ \n## 1. Definitions\n1.1. Derivative Model means all (a) modifications to the Model, (b) works based on the Model, and (c) any other derivative works of the Model. An output is not a Derivative Model. \n1.2. Legal Entity means the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, “control” means (a) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (b) ownership of fifty percent (50%) or more of the outstanding shares, or (c) beneficial ownership of such entity. \n1.3. Model means the machine learning model, software, checkpoints, learnt weights, algorithms, parameters, configuration files and documentation shared under this Agreement. \n1.4. NVIDIA Cosmos Model means a multimodal Model shared under this Agreement. \n1.5. Special-Purpose Model means a Model that is only competent in a narrow set of purpose-specific tasks and should not be used for unintended or general-purpose applications. \n1.6. You or Your means an individual or Legal Entity exercising permissions granted by this Agreement. \n## 2. Conditions for Use, License Grant, AI Ethics and IP Ownership\n### 2.1. Conditions for Use - The Model and any Derivative Model are subject to additional terms as described in Section 2 and Section 3 of this Agreement. - If You institute copyright or patent litigation against any entity alleging that the Model or a Derivative Model constitutes infringement, then any licenses granted will terminate as of the date such litigation is filed. - If You bypass or disable any technical limitation, safety guardrail, encryption, DRM, or authentication mechanism contained in the Model without a substantially similar Guardrail, your rights will terminate. - NVIDIA may designate a Model as a Special-Purpose Model. - NVIDIA may update this Agreement to comply with legal and regulatory requirements. \n### 2.2. License Grant NVIDIA grants You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, revocable license to publicly perform, publicly display, reproduce, use, create derivative works of, make, have made, sell, offer for sale, distribute, and import the Model. \n### 2.3. AI Ethics Use of the Models must be consistent with NVIDIA’s Trustworthy AI terms. \ \n### 2.4. IP Ownership - NVIDIA owns the Model and any Model Derivatives it creates. \ - You own your Model Derivatives. - NVIDIA claims no ownership rights in outputs. \ - Except as expressly granted, NVIDIA reserves all rights. \n## 3. Redistribution\nYou may reproduce and distribute copies of the Model or Derivative Models in any medium, with or without modifications, provided that: \n- 3.1. You must provide recipients with a copy of this Agreement and include this attribution in a “Notice” text file: \ \n “Licensed by NVIDIA Corporation under the NVIDIA Open Model License” \n\n- 3.2. If distributing or making available a NVIDIA Cosmos Model, or products/services derived from it, you must include: \n “Built on NVIDIA Cosmos” \n\n- 3.3. You may add your own copyright statements and license terms for your modifications, provided use still complies with this Agreement. \n## 4. Separate Components The Models may include components licensed under separate legal notices (e.g., Open Source Software Licenses). These terms apply, except where overridden by this Agreement unless required by third-party license terms. \n## 5. Trademarks No permission is granted to use NVIDIA’s trade names, trademarks, or product names, except for reasonable descriptive use. \n## 6. Disclaimer of Warranty The Model is provided “AS IS”, without warranties of any kind, including title, non-infringement, merchantability, or fitness for purpose. You assume risks associated with its use. \ \n## 7. Limitation of Liability NVIDIA is not liable for damages (direct, indirect, incidental, or consequential) arising from use of the Model, unless required by law. \n## 8. Indemnity You will indemnify and hold NVIDIA harmless against claims from third parties arising from your use or distribution of the Model, derivatives, or outputs. \n## 9. Feedback NVIDIA may use any feedback you provide without restriction or compensation. \n## 10. Governing Law This Agreement is governed by U.S. and Delaware law. Courts in Santa Clara County, California, have exclusive jurisdiction, except for urgent injunctive relief. \n## 11. Trade and Compliance You must comply with all export, import, trade, and sanctions laws, including U.S. Export Administration Regulations and OFAC rules." language:

• en

library_name: transformers license: other license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license license_name: nvidia-open-model-license mradermacher: readme_rev: 1 quantized_by: mradermacher tags:

• nvidia
• cosmos
• conversational

---

About

weighted/imatrix quants of https://huggingface.co/nvidia/Cosmos-Reason2-8B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Cosmos-Reason2-8B-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	imatrix	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	2.2	for the desperate
GGUF	i1-IQ1_M	2.4	mostly desperate
GGUF	i1-IQ2_XXS	2.6
GGUF	i1-IQ2_XS	2.8
GGUF	i1-IQ2_S	3.0
GGUF	i1-IQ2_M	3.2
GGUF	i1-Q2K_S	3.2	very low quality
GGUF	i1-Q2K	3.4	IQ3XXS probably better
GGUF	i1-IQ3_XXS	3.5	lower quality
GGUF	i1-IQ3_XS	3.7
GGUF	i1-Q3KS	3.9	IQ3XS probably better
GGUF	i1-IQ3S	3.9	beats Q3K*
GGUF	i1-IQ3_M	4.0
GGUF	i1-Q3KM	4.2	IQ3S probably better
GGUF	i1-Q3KL	4.5	IQ3M probably better
GGUF	i1-IQ4_XS	4.7
GGUF	i1-Q4_0	4.9	fast, low quality
GGUF	i1-IQ4NL	4.9	prefer IQ4XS
GGUF	i1-Q4K_S	4.9	optimal size/speed/quality
GGUF	i1-Q4K_M	5.1	fast, recommended
GGUF	i1-Q4_1	5.3
GGUF	i1-Q5K_S	5.8
GGUF	i1-Q5K_M	6.0
GGUF	i1-Q6K	6.8	practically like static Q6K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

!image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.