DE

DeepSeek-V4-Flash-DSpark-Drafter

DeepSeekGGUF by alessandrobolognaUpdated 2026-08-15
Download on Hugging Face
Parameters19.8B
Context—
Layers—
Architecturedeepseek_v4_flash_dspark_draft
Smallest quant7.0 GB
Quick answer

DeepSeek-V4-Flash-DSpark-Drafter needs about 8.3 GB of memory at Q2_K (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.0 GB (Q2_K) to 10.9 GB (MXFP4).

DeepSeek-V4-Flash-DSpark-Drafter – a lightweight draft module for DeepSeek V4 Flash

DeepSeek-V4-Flash-DSpark-Drafter is a draft module built from the DeepSeek V4 Flash DSpark checkpoint. It is not a standalone language model and contains only the auxiliary drafter weights. The GGUF files are quantized with Q2_K or MXFP4.

Good at

  • Lightweight inference
  • Compatible with DeepSeek V4 Flash
  • Supports 1M‑token context via DSpark

Limits

  • Not a full language model
  • No vision support
  • Requires DeepSeek V4 Flash base

Best for

  • Drafting short text segments
  • Testing DSpark speculative decoding
  • Rapid prototyping of DeepSeek V4 Flash

Who it’s for. Developers and researchers who need a quick, low‑memory draft module to test or extend DeepSeek V4 Flash. It is useful when the full model is unavailable or too large for the target hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.0 GB 8.3 GB
Too big Get file →
Q2_K7.0 GB 8.3 GB
Too big Get file →
MXFP410.9 GB 12.7 GB
Too big Get file →

For 8 GB VRAM, use the Q2_K quant with file size 6.97 GB; it requires about 8.3 GB memory at 8 k context. If more memory is available, the MXFP4 quant (10.9 GB file, 12.7 GB memory) offers higher precision.

What GPU do you need for DeepSeek-V4-Flash-DSpark-Drafter?

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 Q2_K (7.0 GB file, about 8.3 GB in use).
  • 16 GB VRAM: the best quant that fits is MXFP4 (10.9 GB file, about 12.7 GB in use).

Which DeepSeek-V4-Flash-DSpark-Drafter quant should you choose?

Q2_K (7.0 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 Q2_K at 7.0 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

Architecturedeepseek_v4_flash_dspark_draft
Parameters19.8B

Source

Quantized byalessandrobologna
FamilyDeepSeek
Licensemit
Downloads (HF)2,325
Last updated2026-08-15

Frequently asked questions about DeepSeek-V4-Flash-DSpark-Drafter

How much VRAM does DeepSeek-V4-Flash-DSpark-Drafter need?

About 8.3 GB at Q2_K with an 8K context window. That is the 7.0 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-Flash-DSpark-Drafter on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek-V4-Flash-DSpark-Drafter GGUF?

It depends on the quant: Q2_K is 7.0 GB, Q2_K is 7.0 GB, MXFP4 is 10.9 GB.

Where can I download DeepSeek-V4-Flash-DSpark-Drafter GGUF?

The files are on Hugging Face in the alessandrobologna/DeepSeek-V4-Flash-DSpark-Drafter-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-Flash-DSpark-Drafter 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?

Yes, the Q2_K quant requires approximately 8.3 GB memory at 8 k context, which fits within an 8 GB VRAM budget with some headroom.

Is this a full language model?

No, it is only the DSpark auxiliary drafter and does not contain the target model weights.

What license does it use?

The model is released under the MIT license.

Other GGUFs of DeepSeek-V4-Flash-DSpark

Similar models

Browse all →

More from alessandrobologna

All by alessandrobologna →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →