DO

DolphinStar 12.5B Q6 K

DolphinstarGGUF by NikolayKozloffUpdated 2024-04-11
Download on Hugging Face
Parameters12.5B
Context32K
Layers56
Architecturellama
Smallest quant10.2 GB
Quick answer

DolphinStar 12.5B Q6 K needs about 12.6 GB of memory at Q6_K (a 10.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

DolphinStar 12.5B Q6 K is a 12.5B-parameter Dolphinstar model in GGUF format, quantized by NikolayKozloff. Its trained context length is 32K tokens. The repository has 1 quant file, from 10.2 GB (Q6_K) to 10.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K10.2 GB 12.6 GB
Too big Get file →

What GPU do you need for DolphinStar 12.5B Q6 K?

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 Q6_K (10.2 GB file, about 12.6 GB in use).

Which DolphinStar 12.5B Q6 K quant should you choose?

Q6_K (10.2 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

Architecturellama
Parameters12.5B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized byNikolayKozloff
Downloads (HF)40
Last updated2024-04-11

Frequently asked questions about DolphinStar 12.5B Q6 K

How much VRAM does DolphinStar 12.5B Q6 K need?

About 12.6 GB at Q6_K with an 8K context window. That is the 10.2 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 DolphinStar 12.5B Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DolphinStar 12.5B Q6 K GGUF?

It depends on the quant: Q6_K is 10.2 GB.

What context length does DolphinStar 12.5B Q6 K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download DolphinStar 12.5B Q6 K GGUF?

The files are on Hugging Face in the NikolayKozloff/DolphinStar-12.5B-Q6_K-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 from NikolayKozloff

All by NikolayKozloff →

More Dolphinstar models

All Dolphinstar →

Other medium models

All medium models →