RA

RakutenAI 7B chat Quantized model

RakutenaiGGUF by baxinUpdated 2024-04-02
Download on Hugging Face
Parameters7.37B
Context32K
Layers32
Architecturellama
Smallest quant4.5 GB
Quick answer

RakutenAI 7B chat Quantized model needs about 6.0 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 4.5 GB (Q4_K_M) to 14.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

RakutenAI 7B chat Quantized model is a 7.37B-parameter Rakutenai model in GGUF format, quantized by baxin. Its trained context length is 32K tokens. The repository has 5 quant files, from 4.5 GB (Q4_K_M) to 14.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.5 GB 6.0 GB
Fits Get file →
Q5_K_S5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.2 GB 6.8 GB
Fits Get file →
Q6_K6.0 GB 7.6 GB
Tight Get file →
F1614.7 GB 16.3 GB
Too big Get file →

What GPU do you need for RakutenAI 7B chat Quantized model?

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: the best quant that fits is Q4_K_M (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.6 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.7 GB file, about 16.3 GB in use).

Which RakutenAI 7B chat Quantized model quant should you choose?

Q4_K_M is the usual starting point for RakutenAI 7B chat Quantized model: it balances file size and quality well. Here it is a 4.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.37B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybaxin
FamilyRakutenai
Licenseapache-2.0
Downloads (HF)14
Last updated2024-04-02

Frequently asked questions about RakutenAI 7B chat Quantized model

How much VRAM does RakutenAI 7B chat Quantized model need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.5 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 RakutenAI 7B chat Quantized model on an 8 GB GPU?

Yes, with Q6_K: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RakutenAI 7B chat Quantized model GGUF?

It depends on the quant: Q4_K_M is 4.5 GB, Q5_K_S is 5.1 GB, Q5_K_M is 5.2 GB, Q6_K is 6.0 GB, F16 is 14.7 GB.

What context length does RakutenAI 7B chat Quantized model 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 RakutenAI 7B chat Quantized model GGUF?

The files are on Hugging Face in the baxin/RakutenAI-7B-chat-Quantized-model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does RakutenAI 7B chat Quantized model use?

Hugging Face lists the license as apache-2.0. 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 baxin

All by baxin →

More Rakutenai models

All Rakutenai →

Other small models

All small models →