Cosmos-Reason1-7B needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 26 quants, from 2.1 GB (IQ1_S) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Cosmos-Reason1-7B: 7B‑parameter vision‑language model for physical AI reasoning
Cosmos-Reason1-7B is a 7.62B‑parameter VLM designed for robotics and physical AI. It processes images or video with a vision encoder and projector, then applies chain‑of‑thought reasoning to generate step‑by‑step answers. The model is ready for commercial use.
Good at
- Vision‑language reasoning
- Physical world planning
- Chain‑of‑thought explanations
Limits
- No vision support in the base model
- Requires 8 k context for full performance
- License is other, not open source
Best for
- Robot planning and decision making
- Video analytics agents
- Data curation and annotation
Who it’s for. Developers building robotics or physical AI systems that need spatial‑temporal reasoning. The model can serve as a planning engine for embodied agents and as an analytics tool for video data.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.1 GB | 3.0 GB | Fits | Get file → | |
| IQ1_M | 2.2 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XXS | 2.4 GB | 3.4 GB | Fits | Get file → | |
| IQ2_M | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q2_K_L | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q2_K_XL | 3.2 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_XL | 4.0 GB | 5.0 GB | Fits | Get file → | |
| IQ4_XS | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_XL | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.8 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_XL | 5.5 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q6_K_XL | 7.0 GB | 7.9 GB | Tight | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| Q8_K_XL | 10.2 GB | 11.2 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.07 GB, 3 GB memory at 8 k context) or IQ1_M (2.2 GB, 3.2 GB). For 16 GB VRAM, Q4_K_M (4.68 GB, 5.7 GB) or Q5_K_S (5.32 GB, 6.3 GB) provide a good balance of size and performance. Higher‑precision quants such as Q8_0 (8.1 GB, 9.1 GB) need 24 GB VRAM or more.
What GPU do you need for Cosmos-Reason1-7B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q2_K (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K_XL (7.0 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_K_XL (10.2 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K_XL (10.2 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which Cosmos-Reason1-7B quant should you choose?
Q4_K_M is the usual starting point for Cosmos-Reason1-7B: it balances file size and quality well. Here it is a 4.7 GB file.
The Q8_0 file is 8.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Cosmos-Reason1-7B
How much VRAM does Cosmos-Reason1-7B need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Cosmos-Reason1-7B on an 8 GB GPU?
Yes, with Q6_K_XL: the 7.0 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Cosmos-Reason1-7B GGUF?
It depends on the quant: IQ1_S is 2.1 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_M is 2.9 GB, Q2_K is 3.0 GB, Q2_K_L is 3.1 GB and 20 more.
What context length does Cosmos-Reason1-7B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Cosmos-Reason1-7B GGUF?
The files are on Hugging Face in the unsloth/Cosmos-Reason1-7B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Cosmos-Reason1-7B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Cosmos-Reason1-7B on 8 GB VRAM?
Yes, using the IQ1_S or IQ1_M quant, which are 2.07 GB and 2.2 GB respectively and require about 3 GB memory at 8 k context.
Does the model support vision input?
Yes, it uses a vision encoder and projector to process images or video before language reasoning.
What context length is needed for full performance?
The model was trained on 128000 tokens and requires an 8 k context for optimal operation.