DE

DeepSeek V4.1 Flash DS4 IQ2

DeepSeekGGUF by ivanfioravantiUpdated 2026-10-18
Download on Hugging Face
Parameters755B
Context—
Layers32
Architecturedeepseek4-vision
Smallest quant1.0 GB
Quick answer

DeepSeek V4.1 Flash DS4 IQ2 needs about 9.5 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 3 quants, from 1.0 GB to 365.7 GB.

DeepSeek V4.1 Flash DS4 IQ2 – a 755B parameter model with reduced expert size

DeepSeek V4.1 Flash DS4 IQ2 is a 755 billion‑parameter model built on the deepseek4‑vision architecture. It is a quantized version of DeepSeek‑V4.1‑Flash‑1017, using an importance‑matrix IQ2 recipe to reduce routed expert size. The model is released under the MIT license.

Good at

  • Reasoning
  • Coding
  • Agentic tasks

Limits

  • No vision support in GGUF
  • Requires DS4 runtime
  • Large memory for full precision

Best for

  • Local inference on high‑memory systems
  • Fine‑tuning with DS4
  • Research on expert quantization

Who it’s for. Users who need a large DeepSeek model with reduced memory footprint for local deployment. It is suitable for developers and researchers with access to DS4 runtime and sufficient RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 2.5 GB
Fits Get file →
MXFP48.0 GB 9.5 GB
Too big Get file →
—365.7 GB 367.3 GB
Too big Get file →

For 8 GB VRAM, use the MXFP4 quant file (7.97 GB, 9.5 GB RAM). For 16 GB VRAM, the unknown 0.97 GB quant file (2.5 GB RAM) is suitable. For large‑scale deployment, the 365.71 GB quant file (367.3 GB RAM) is available.

What GPU do you need for DeepSeek V4.1 Flash DS4 IQ2?

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 (1.0 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.5 GB in use).
  • 12 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.5 GB in use).
  • 16 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.5 GB in use).
  • 24 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.5 GB in use).
  • 32 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.5 GB in use).
  • 48 GB VRAM: the best quant that fits is MXFP4 (8.0 GB file, about 9.5 GB in use).

Which DeepSeek V4.1 Flash DS4 IQ2 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.

If memory is tight, the smallest file is the first one in the table at 1.0 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

Architecturedeepseek4-vision
Parameters755B
Layers32
KV cache (fp16)128 KB per token

Source

Quantized byivanfioravanti
FamilyDeepSeek
Licensemit
Downloads (HF)989
Last updated2026-10-18

Frequently asked questions about DeepSeek V4.1 Flash DS4 IQ2

How much VRAM does DeepSeek V4.1 Flash DS4 IQ2 need?

About 9.5 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 DS4 IQ2 on an 8 GB GPU?

Yes, with the smaller files: the 1.0 GB file needs about 2.5 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 DS4 IQ2 GGUF?

It depends on the quant: file is 1.0 GB, MXFP4 is 8.0 GB, file is 365.7 GB.

Where can I download DeepSeek V4.1 Flash DS4 IQ2 GGUF?

The files are on Hugging Face in the ivanfioravanti/DeepSeek-V4.1-Flash-DS4-IQ2 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 DS4 IQ2 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 MXFP4 quant file is 7.97 GB, which fits 8 GB VRAM, but requires 9.5 GB RAM. The 0.97 GB quant file also fits VRAM but needs 2.5 GB RAM.

Does this model support vision tasks?

The GGUF does not include vision support; it is a text‑only model.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of DeepSeek-V4.1-Flash-1017

Similar models

Browse all →

More from ivanfioravanti

All by ivanfioravanti →

More DeepSeek models

All DeepSeek →

Other large models

All large models →