DE

DeepSeek 1.5B

DeepSeekGGUF by ThePradipUpdated 2025-01-28
Download on Hugging Face
Parameters7.62B
Context986K
Layers28
Architectureqwen2
Smallest quant3.9 GB
Quick answer

DeepSeek 1.5B needs about 4.8 GB of memory at TQ2_0 (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.9 GB (TQ2_0) to 8.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

DeepSeek 1.5B is a 7.62B-parameter DeepSeek model in GGUF format, quantized by ThePradip. Its trained context length is 986K tokens. The repository has 2 quant files, from 3.9 GB (TQ2_0) to 8.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_03.9 GB 4.8 GB
Fits Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →

What GPU do you need for DeepSeek 1.5B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is TQ2_0 (3.9 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is TQ2_0 (3.9 GB file, about 4.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).

Which DeepSeek 1.5B quant should you choose?

TQ2_0 (3.9 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

Architectureqwen2
Parameters7.62B
Layers28
Trained context1,010,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized byThePradip
FamilyDeepSeek
Licenseapache-2.0
Downloads (HF)55
Last updated2025-01-28

Frequently asked questions about DeepSeek 1.5B

How much VRAM does DeepSeek 1.5B need?

About 4.8 GB at TQ2_0 with an 8K context window. That is the 3.9 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 1.5B on an 8 GB GPU?

Yes, with TQ2_0: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek 1.5B GGUF?

It depends on the quant: TQ2_0 is 3.9 GB, Q8_0 is 8.1 GB.

What context length does DeepSeek 1.5B support?

The GGUF header lists a trained context length of 1,010,000 tokens (986K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download DeepSeek 1.5B GGUF?

The files are on Hugging Face in the ThePradip/DeepSeek-1.5B-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 1.5B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ThePradip

All by ThePradip →

More DeepSeek models

All DeepSeek →

Other small models

All small models →