DE

deepseek-coder-33b-instruct

DeepSeekGGUF by int2ehUpdated 2024-04-30
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant23.0 GB
Quick answer

deepseek-coder-33b-instruct needs about 25.5 GB of memory at Q5_K_S (a 23.0 GB file) with an 8K context window, so it fits on a 32 GB GPU.

deepseek-coder-33b-instruct is a 33.3B-parameter DeepSeek model in GGUF format, quantized by int2eh. Its trained context length is 16K tokens. The repository has 1 quant file, from 23.0 GB (Q5_K_S) to 23.0 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S23.0 GB 25.5 GB
Too big Get file →

What GPU do you need for deepseek-coder-33b-instruct?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q5_K_S (23.0 GB file, about 25.5 GB in use).

Which deepseek-coder-33b-instruct quant should you choose?

Q5_K_S (23.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.3B
Layers62
Trained context16,384 tokens
KV cache (fp16)248 KB per token

Source

Quantized byint2eh
FamilyDeepSeek
Licenseother
Downloads (HF)71
Last updated2024-04-30

Frequently asked questions about deepseek-coder-33b-instruct

How much VRAM does deepseek-coder-33b-instruct need?

About 25.5 GB at Q5_K_S with an 8K context window. That is the 23.0 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-coder-33b-instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of deepseek-coder-33b-instruct GGUF?

It depends on the quant: Q5_K_S is 23.0 GB.

What context length does deepseek-coder-33b-instruct support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.

Where can I download deepseek-coder-33b-instruct GGUF?

The files are on Hugging Face in the int2eh/deepseek-coder-33b-instruct-Q5_K_S-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-33b-instruct 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.

Similar models

Browse all →

More from int2eh

All by int2eh →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →