RA

Rain 2x7B MoE 32k v0.1

RainGGUF by yuuko-ethUpdated 2024-01-21
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant7.3 GB
Quick answer

Rain 2x7B MoE 32k v0.1 needs about 12.1 GB of memory at Q6_K (a 10.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 7.3 GB (Q4_0) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Rain 2x7B MoE 32k v0.1 is a 12.9B-parameter Rain model in GGUF format, quantized by yuuko-eth. Its trained context length is 32K tokens. The repository has 3 quant files, from 7.3 GB (Q4_0) to 13.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.3 GB 8.9 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →
Q8_013.7 GB 15.3 GB
Too big Get file →

What GPU do you need for Rain 2x7B MoE 32k v0.1?

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 Q4_0 (7.3 GB file, about 8.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).

Which Rain 2x7B MoE 32k v0.1 quant should you choose?

Q6_K (10.6 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.

If memory is tight, the smallest file is Q4_0 at 7.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byyuuko-eth
FamilyRain
Licenseunknown
Downloads (HF)218
Last updated2024-01-21

Frequently asked questions about Rain 2x7B MoE 32k v0.1

How much VRAM does Rain 2x7B MoE 32k v0.1 need?

About 12.1 GB at Q6_K with an 8K context window. That is the 10.6 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 Rain 2x7B MoE 32k v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Rain 2x7B MoE 32k v0.1 GGUF?

It depends on the quant: Q4_0 is 7.3 GB, Q6_K is 10.6 GB, Q8_0 is 13.7 GB.

What context length does Rain 2x7B MoE 32k v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Rain 2x7B MoE 32k v0.1 GGUF?

The files are on Hugging Face in the yuuko-eth/Rain-2x7B-MoE-32k-v0.1-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 Rain 2x7B MoE 32k v0.1 use?

Hugging Face lists the license as unknown. 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 yuuko-eth

All by yuuko-eth →

More Rain models

All Rain →

Other medium models

All medium models →