DeepSeek V4.1 Flash GSQ RCO needs about 10.9 GB of memory at its main file (a 9.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.3 GB to 415.8 GB.
DeepSeek V4.1 Flash GSQ RCO – a 748‑billion‑parameter GGUF model with compressed KV cache
DeepSeek V4.1 Flash GSQ RCO is a 748‑billion‑parameter model quantized to 3.0 bits per weight. The GGUF files include the backbone, DSpark draft model and BF16 vision projector. The model is released under the MIT license.
Good at
- Large‑context text generation
- Efficient KV cache compression
- Multimodal vision support
Limits
- No explicit context length limit provided
- Requires large host memory for Engram tables
- No vision support in the quantized version
Best for
- Agents needing long‑form text generation
- Applications requiring efficient KV usage
- Projects using multimodal inputs
Who it’s for. Developers and researchers building agents or applications that need a large‑parameter model with efficient KV caching and multimodal capabilities. The model is suitable for environments where host memory can accommodate the Engram tables and the large GGUF file.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 9.3 GB | 10.9 GB | Too big | Get file → | |
| — | 415.8 GB | 466.2 GB | Too big | Get file → |
For a 8‑GB VRAM budget, use the 9.32‑GB GGUF file (est. 10.9‑GB memory at 8k context). For larger memory budgets, the 415.76‑GB file (est. 466.2‑GB memory at 8k context) provides the full model with DSpark and vision projector.
What GPU do you need for DeepSeek V4.1 Flash GSQ RCO?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V4.1 Flash GSQ RCO
How much VRAM does DeepSeek V4.1 Flash GSQ RCO need?
About 10.9 GB at its main file with an 8K context window. That is the 9.3 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 GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4.1 Flash GSQ RCO GGUF?
It depends on the quant: file is 9.3 GB, file is 415.8 GB.
Where can I download DeepSeek V4.1 Flash GSQ RCO GGUF?
The files are on Hugging Face in the pfeifferj/DeepSeek-V4.1-Flash-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 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 this model on 8 GB VRAM?
The 9.32‑GB GGUF file requires approximately 10.9‑GB memory at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision inputs?
The GGUF quantization includes a BF16 vision projector, so it can process images.
What license does the model use?
The model is released under the MIT license.