DeepSeek V4.1 Flash needs about 416.5 GB of memory at IQ2_XXS (a 371.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 0.8 GB to 508.0 GB (MXFP4).
DeepSeek V4.1 Flash – 748B parameter LLM with advanced KV cache compression
DeepSeek V4.1 Flash is a 748 billion‑parameter model released under the MIT license. It supports up to 8 k context length and offers multiple quantization options for different memory budgets. The model is available in GGUF format for llama.cpp.
Good at
- Large‑scale text generation
- Efficient KV cache usage
- Low‑memory inference
Limits
- No vision support in this GGUF build
- Requires custom llama.cpp build
- Limited to 8 k context
Best for
- Chatbot back‑ends
- Content drafting
- Research prototyping
Who it’s for. Engineers and researchers needing a high‑capacity language model that can run on local hardware with reduced memory footprints. The model is suitable for developers familiar with llama.cpp and custom builds.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.8 GB | 1.4 GB | Fits | Get file → | |
| — | 8.0 GB | 9.4 GB | Too big | Get file → | |
| Q2_K | 335.4 GB (10 parts) | 376.1 GB | Too big | Get file → | |
| IQ2_XXS | 371.4 GB (10 parts) | 416.5 GB | Too big | Get file → | |
| Q2_K | 413.4 GB (10 parts) | 463.5 GB | Too big | Get file → | |
| IQ3_XS | 434.0 GB (10 parts) | 486.6 GB | Too big | Get file → | |
| MXFP4 | 508.0 GB (10 parts) | 569.4 GB | Too big | Get file → |
For 8 GB VRAM, use the Q2_K shard set (10 shards, 413.39 GB file size, 463.5 GB memory at 8 k context). For 16 GB VRAM, the IQ3_XS shards (10 shards, 434.02 GB file size, 486.6 GB memory) provide a balance between size and performance. The MXFP4 shards (10 shards, 507.95 GB file size, 569.4 GB memory) offer the highest precision for larger GPUs.
What GPU do you need for DeepSeek V4.1 Flash?
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: the best quant that fits is the main file (0.8 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.8 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.8 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 9.4 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 9.4 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 9.4 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 9.4 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 9.4 GB in use).
Which DeepSeek V4.1 Flash quant should you choose?
IQ2_XXS (371.4 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 the first one in the table at 0.8 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 DeepSeek V4.1 Flash
How much VRAM does DeepSeek V4.1 Flash need?
About 416.5 GB at IQ2_XXS with an 8K context window. That is the 371.4 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 on an 8 GB GPU?
Yes, with the smaller files: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek V4.1 Flash GGUF?
It depends on the quant: file is 0.8 GB, file is 8.0 GB, Q2_K is 335.4 GB, IQ2_XXS is 371.4 GB, Q2_K is 413.4 GB, IQ3_XS is 434.0 GB and 1 more.
Where can I download DeepSeek V4.1 Flash GGUF?
The files are on Hugging Face in the smalinin/DeepSeek-V4.1-Flash-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 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 on 8 GB VRAM?
Use the Q2_K quantized shards; the estimated memory at 8 k context is 463.5 GB, which is not feasible on 8 GB VRAM. A smaller quant or a different model is required.
Does this model support image input?
No, the GGUF build does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license.