Dots3 Note Prev needs about 172.4 GB of memory at Q4_K_M (a 171.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.6 GB to 298.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
280B parameter Mixture‑of‑Experts model with vision and long‑context support
Dots3 Note Prev is a 280 billion‑parameter Mixture‑of‑Experts model. It supports up to 512 K context tokens and multimodal inputs including text, image, video, and audio. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Long‑context reasoning
- Multimodal understanding
- Agent‑style task execution
Limits
- Requires large VRAM for high‑quality quants
- No native vision support without mmproj
- Limited to text output
Best for
- Complex document analysis
- Multimodal content generation
- Long‑form dialogue
Who it’s for. Engineers and researchers needing a large, multimodal LLM with extensive context. The model is suitable for developers building AI assistants or content analysis tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.6 GB | 1.9 GB | Fits | Get file → | |
| IQ1_S | 58.6 GB (2 parts) | 59.9 GB | Too big | Get file → | |
| IQ1_M | 65.3 GB (2 parts) | 66.6 GB | Too big | Get file → | |
| IQ2_XXS | 75.8 GB (2 parts) | 77.1 GB | Too big | Get file → | |
| IQ2_XS | 84.3 GB (3 parts) | 85.6 GB | Too big | Get file → | |
| IQ2_S | 86.0 GB (3 parts) | 87.3 GB | Too big | Get file → | |
| IQ2_M | 94.8 GB (3 parts) | 96.2 GB | Too big | Get file → | |
| Q2_K | 99.4 GB (3 parts) | 100.8 GB | Too big | Get file → | |
| Q2_K_L | 100.2 GB (3 parts) | 101.5 GB | Too big | Get file → | |
| IQ3_XXS | 117.5 GB (3 parts) | 118.8 GB | Too big | Get file → | |
| Q3_K_S | 122.7 GB (4 parts) | 124.0 GB | Too big | Get file → | |
| IQ3_XS | 128.3 GB (4 parts) | 129.6 GB | Too big | Get file → | |
| Q3_K_M | 128.6 GB (4 parts) | 129.9 GB | Too big | Get file → | |
| Q3_K_L | 133.8 GB (4 parts) | 135.1 GB | Too big | Get file → | |
| IQ3_M | 134.1 GB (4 parts) | 135.5 GB | Too big | Get file → | |
| Q3_K_XL | 134.5 GB (4 parts) | 135.8 GB | Too big | Get file → | |
| IQ4_XS | 150.4 GB (4 parts) | 151.7 GB | Too big | Get file → | |
| IQ4_NL | 159.0 GB (5 parts) | 160.3 GB | Too big | Get file → | |
| Q4_0 | 159.4 GB (5 parts) | 160.7 GB | Too big | Get file → | |
| Q4_K_S | 164.5 GB (5 parts) | 165.8 GB | Too big | Get file → | |
| Q4_K_M | 171.1 GB (5 parts) | 172.4 GB | Too big | Get file → | |
| Q4_K_L | 171.7 GB (5 parts) | 173.0 GB | Too big | Get file → | |
| Q4_1 | 176.1 GB (5 parts) | 177.5 GB | Too big | Get file → | |
| Q5_K_S | 193.8 GB (5 parts) | 195.1 GB | Too big | Get file → | |
| Q5_K_M | 200.4 GB (6 parts) | 201.7 GB | Too big | Get file → | |
| Q6_K | 242.3 GB (7 parts) | 243.6 GB | Too big | Get file → | |
| Q8_0 | 298.4 GB (8 parts) | 299.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (58.58 GB, ~60 GB memory at 8K context). For 16 GB VRAM, Q4_K_M (171.11 GB, ~172 GB memory) offers a balance of size and performance. For 24 GB VRAM, Q5_K_M (200.41 GB, ~202 GB memory) provides higher fidelity.
What GPU do you need for Dots3 Note Prev?
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 the main file (0.6 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.9 GB in use).
Which Dots3 Note Prev quant should you choose?
Q4_K_M is the usual starting point for Dots3 Note Prev: it balances file size and quality well. Here it is a 171.1 GB file.
The Q8_0 file is 298.4 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 the first one in the table at 0.6 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Dots3 Note Prev
How much VRAM does Dots3 Note Prev need?
About 172.4 GB at Q4_K_M with an 8K context window. That is the 171.1 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 Dots3 Note Prev on an 8 GB GPU?
Yes, with the smaller files: the 0.6 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dots3 Note Prev GGUF?
It depends on the quant: file is 0.6 GB, IQ1_S is 58.6 GB, IQ1_M is 65.3 GB, IQ2_XXS is 75.8 GB, IQ2_XS is 84.3 GB, IQ2_S is 86.0 GB and 21 more.
What context length does Dots3 Note Prev support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download Dots3 Note Prev GGUF?
The files are on Hugging Face in the bartowski/dots-studio_dots3-note-prev-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 Dots3 Note Prev use?
Hugging Face lists the license as apache-2.0. 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 Dots3 Note Prev on 8 GB VRAM?
Only the smallest quant IQ1_S can be loaded, but it will require ~60 GB of VRAM at 8K context, so 8 GB is insufficient.
Does the model support image input?
Yes, image and audio input are supported via the mmproj projector files that accompany the GGUF quants.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.