DC

dclm

DclmGGUF by xinshuoUpdated 2024-09-29
Download on Hugging Face
Parameters6.89B
Context2K
Layers32
Architectureopenlm
Smallest quant13.8 GB
Quick answer

dclm needs about 14.4 GB of memory at F32 (a 13.8 GB file) with an 8K context window, so it fits on a 16 GB GPU.

dclm is a 6.89B-parameter Dclm model in GGUF format, quantized by xinshuo. Its trained context length is 2K tokens. The repository has 1 quant file, from 13.8 GB (F32) to 13.8 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F3213.8 GB 14.3 GB
Too big Get file →

What GPU do you need for dclm?

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: the best quant that fits is F32 (13.8 GB file, about 14.4 GB in use).

Which dclm quant should you choose?

F32 (13.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureopenlm
Parameters6.89B
Layers32
Trained context2,048 tokens
KV cache (fp16)16 KB per token

Source

Quantized byxinshuo
FamilyDclm
Downloads (HF)21
Last updated2024-09-29

Frequently asked questions about dclm

How much VRAM does dclm need?

About 14.4 GB at F32 with an 8K context window. That is the 13.8 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 dclm on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dclm GGUF?

It depends on the quant: F32 is 13.8 GB.

What context length does dclm support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download dclm GGUF?

The files are on Hugging Face in the xinshuo/dclm.gguf 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 Dclm models

All Dclm →

Other small models

All small models →