DE

deepseek coder 6.7b vala

DeepSeekGGUF by scowenUpdated 2024-10-09
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant7.2 GB
Quick answer

deepseek coder 6.7b vala needs about 12.0 GB of memory at Q8_0 (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 7.2 GB (Q8_0) to 8.1 GB (Q8_0).

deepseek coder 6.7b vala is a 6.74B-parameter DeepSeek model in GGUF format, quantized by scowen. Its trained context length is 16K tokens. The repository has 6 quant files, from 7.2 GB (Q8_0) to 8.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.2 GB 12.0 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
Q8_08.1 GB 12.9 GB
Too big Get file →

What GPU do you need for deepseek coder 6.7b vala?

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 Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 12.9 GB in use).

Which deepseek coder 6.7b vala quant should you choose?

Q8_0 (7.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q8_0 at 7.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized byscowen
FamilyDeepSeek
Downloads (HF)58
Last updated2024-10-09

Frequently asked questions about deepseek coder 6.7b vala

How much VRAM does deepseek coder 6.7b vala need?

About 12.0 GB at Q8_0 with an 8K context window. That is the 7.2 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 6.7b vala on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of deepseek coder 6.7b vala GGUF?

It depends on the quant: Q8_0 is 7.2 GB, Q8_0 is 7.2 GB, Q8_0 is 7.2 GB, Q8_0 is 7.2 GB, Q8_0 is 7.2 GB, Q8_0 is 8.1 GB.

What context length does deepseek coder 6.7b vala support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download deepseek coder 6.7b vala GGUF?

The files are on Hugging Face in the scowen/deepseek-coder-6.7b-vala 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 DeepSeek models

All DeepSeek →

Other small models

All small models →