RO

Rose 20B

RoseGGUF by mradermacherUpdated 2024-11-18
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant40.0 GB
Quick answer

Rose 20B needs about 50.9 GB of memory at its main file (a 40.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

Rose 20B is a 20B-parameter Rose model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 1 quant file, from 40.0 GB to 40.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—40.0 GB 45.7 GB
Too big Get file →

What GPU do you need for Rose 20B?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
FamilyRose
Base modeltavtav/Rose-20B
Licensellama2
Downloads (HF)49
Last updated2024-11-18

Frequently asked questions about Rose 20B

How much VRAM does Rose 20B need?

About 50.9 GB at its main file with an 8K context window. That is the 40.0 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 Rose 20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Rose 20B GGUF?

It depends on the quant: file is 40.0 GB.

What context length does Rose 20B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download Rose 20B GGUF?

The files are on Hugging Face in the mradermacher/Rose-20B-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 Rose 20B use?

Hugging Face lists the license as llama2. 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 Rose-20B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rose models

All Rose →

Other medium models

All medium models →