DE

DeepSeek FGS 003

DeepSeekGGUF by seossineUpdated 2025-02-13
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant9.0 GB
Quick answer

DeepSeek FGS 003 needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

DeepSeek FGS 003 is a 14.8B-parameter DeepSeek model in GGUF format, quantized by seossine. Its trained context length is 128K tokens. The repository has 1 quant file, from 9.0 GB (Q4_K_M) to 9.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M9.0 GB 11.1 GB
Too big Get file →

What GPU do you need for DeepSeek FGS 003?

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: 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 Q4_K_M (9.0 GB file, about 11.1 GB in use).

Which DeepSeek FGS 003 quant should you choose?

Q4_K_M is the usual starting point for DeepSeek FGS 003: it balances file size and quality well. Here it is a 9.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byseossine
FamilyDeepSeek
Downloads (HF)30
Last updated2025-02-13

Frequently asked questions about DeepSeek FGS 003

How much VRAM does DeepSeek FGS 003 need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 FGS 003 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek FGS 003 GGUF?

It depends on the quant: Q4_K_M is 9.0 GB.

What context length does DeepSeek FGS 003 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download DeepSeek FGS 003 GGUF?

The files are on Hugging Face in the seossine/DeepSeek-FGS-003 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from seossine

All by seossine →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →