RU

RubMistNemo

RubmistnemoGGUF by TsaricUpdated 2024-09-29
Download on Hugging Face
Parameters13B
Context32K
Layers40
Architecturellama
Smallest quant9.2 GB
Quick answer

RubMistNemo needs about 16.4 GB of memory at Q5_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 9.2 GB (Q5_K_M) to 26.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

RubMistNemo is a 13B-parameter Rubmistnemo model in GGUF format, quantized by Tsaric. Its trained context length is 32K tokens. The repository has 2 quant files, from 9.2 GB (Q5_K_M) to 26.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
BF1626.0 GB 33.2 GB
Too big Get file →

What GPU do you need for RubMistNemo?

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: the best quant that fits is Q5_K_M (9.2 GB file, about 16.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (9.2 GB file, about 16.4 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (26.0 GB file, about 33.2 GB in use).

Which RubMistNemo quant should you choose?

Q5_K_M (9.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTsaric
Downloads (HF)9
Last updated2024-09-29

Frequently asked questions about RubMistNemo

How much VRAM does RubMistNemo need?

About 16.4 GB at Q5_K_M with an 8K context window. That is the 9.2 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 RubMistNemo on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RubMistNemo GGUF?

It depends on the quant: Q5_K_M is 9.2 GB, BF16 is 26.0 GB.

What context length does RubMistNemo support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download RubMistNemo GGUF?

The files are on Hugging Face in the Tsaric/RubMistNemo 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 Tsaric

All by Tsaric →

Other medium models

All medium models →