DeepSeek V4.1 Flash needs about 9.4 GB of memory at MXFP4 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.0 GB (MXFP4) to 403.5 GB (MXFP4).
DeepSeek V4.1 Flash – a large‑parameter text model with efficient KV cache
DeepSeek V4.1 Flash is a 748‑billion‑parameter text model built for mx-llama.cpp. It uses compressed sparse attention and FP4 KV caching to reduce memory usage. The model is released under the MIT license and contains no vision components.
Good at
- Large context handling
- Efficient KV cache compression
- Sparse attention with low memory footprint
Limits
- No vision support
- Requires large VRAM for full model
- Limited to text generation
Best for
- Long‑form text generation
- Agentic workloads with heavy input
- Inference on multi‑GPU setups
Who it’s for. Developers needing a high‑parameter text model that can run on multi‑GPU systems with layer or tensor parallelism. The model is suitable for research and production inference where memory efficiency is critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 8.0 GB | 9.4 GB | Too big | Get file → | |
| MXFP4 | 403.5 GB (12 parts) | 452.4 GB | Too big | Get file → |
For 8‑GB VRAM use the 7.97‑GB MXFP4 file; it requires about 9.4‑GB VRAM at 8k context. For larger memory budgets the 403.5‑GB MXFP4 shard set is available, needing roughly 452.4‑GB VRAM at 8k context. Estimates are approximate.
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: 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 MXFP4 (8.0 GB file, about 9.4 GB in use).
- 16 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.4 GB in use).
- 24 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.4 GB in use).
- 32 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.4 GB in use).
- 48 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.4 GB in use).
Which DeepSeek V4.1 Flash quant should you choose?
MXFP4 (8.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
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 9.4 GB at MXFP4 with an 8K context window. That is the 8.0 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?
Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4.1 Flash GGUF?
It depends on the quant: MXFP4 is 8.0 GB, MXFP4 is 403.5 GB.
What context length does DeepSeek V4.1 Flash support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download DeepSeek V4.1 Flash GGUF?
The files are on Hugging Face in the mxxm-t/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?
No. The smallest quantized file requires about 9.4‑GB VRAM at 8k context, so 8 GB is insufficient.
Does the model support image input?
No. The GGUF files contain only the text model; the vision tower is not included.
What license applies to this model?
The model is released under the MIT license.