DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO needs about 139.4 GB of memory at IQ2_XXS (a 138.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 120.7 GB (IQ1_M) to 155.2 GB (IQ2_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO – 763B MoE LLM in GGUF format
DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO is a 763.2B‑parameter sparse mixture‑of‑experts model with 384 experts per layer and a 1M‑token context window. The GGUF files use non‑uniform GSQ‑RCO quantization, providing three size options. The model is released under the MIT license.
Good at
- Reasoning
- Tool usage
- Large context handling
Limits
- Requires 12 GB VRAM for full model
- No vision support
- Large memory footprint
Best for
- Local inference on single GPU
- Research on MoE architectures
- Testing low‑bit quantization
Who it’s for. Researchers and developers who need a large‑scale MoE model for local inference and want to experiment with non‑uniform quantization. The model is suitable for those with a single GPU and sufficient VRAM to run the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 120.7 GB (4 parts) | 121.9 GB | Too big | Get file → | |
| IQ2_XXS | 138.2 GB (4 parts) | 139.4 GB | Too big | Get file → | |
| IQ2_XS | 155.2 GB (4 parts) | 156.4 GB | Too big | Get file → |
For 12 GB VRAM, IQ1_M (file size 120.72 GB, estimated 121.9 GB at 8 k context) is the smallest option. IQ2_XXS (138.24 GB, 139.4 GB) offers a balance between size and precision. IQ2_XS (155.23 GB, 156.4 GB) provides the highest precision but requires the most memory. Estimates are approximate.
What GPU do you need for DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO quant should you choose?
IQ2_XXS (138.2 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_M at 120.7 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
Frequently asked questions about DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO
How much VRAM does DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO need?
About 139.4 GB at IQ2_XXS with an 8K context window. That is the 138.2 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 DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 121.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF?
It depends on the quant: IQ1_M is 120.7 GB, IQ2_XXS is 138.2 GB, IQ2_XS is 155.2 GB.
What context length does DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF?
The files are on Hugging Face in the AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-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 DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO use?
Hugging Face lists the license as mit. 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 DeepSeek V4.1 Flash 1017 on a single 12 GB GPU?
Yes, the model is designed to run on a single GPU with 12 GB of VRAM using the provided GGUF shards.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license.