DE

DeepSeek Coder V2 Lite Base

DeepSeekGGUF by ijohn07Updated 2024-09-09
Download on Hugging Face
Parameters15.7B
Context160K
Layers27
Architecturedeepseek2
Smallest quant14.1 GB
Quick answer

DeepSeek Coder V2 Lite Base needs about 16.8 GB of memory at Q6_K (a 14.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.1 GB.

DeepSeek Coder V2 Lite Base is a 15.7B-parameter DeepSeek model in GGUF format, quantized by ijohn07. Its trained context length is 160K tokens. The repository has 1 quant file, from 14.1 GB (Q6_K) to 14.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K14.1 GB 16.8 GB
Too big Get file →

What GPU do you need for DeepSeek Coder V2 Lite Base?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 16.8 GB in use).

Which DeepSeek Coder V2 Lite Base quant should you choose?

Q6_K (14.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters15.7B (approximate, mixture of experts)
Layers27
Trained context163,840 tokens
KV cache (fp16)270 KB per token

Source

Quantized byijohn07
FamilyDeepSeek
Licenseother
Downloads (HF)54
Last updated2024-09-09

Frequently asked questions about DeepSeek Coder V2 Lite Base

How much VRAM does DeepSeek Coder V2 Lite Base need?

About 16.8 GB at Q6_K with an 8K context window. That is the 14.1 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 Coder V2 Lite Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek Coder V2 Lite Base GGUF?

It depends on the quant: Q6_K is 14.1 GB.

What context length does DeepSeek Coder V2 Lite Base support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.1 GB at 32K.

Where can I download DeepSeek Coder V2 Lite Base GGUF?

The files are on Hugging Face in the ijohn07/DeepSeek-Coder-V2-Lite-Base-Q6_K-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 Coder V2 Lite Base use?

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

Other GGUFs of DeepSeek-Coder-V2-Lite-Base

Similar models

Browse all →

More from ijohn07

All by ijohn07 →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →