GE

navarasa-malayalam-gguf

GemmaGGUF by animaRegemUpdated 2024-07-05
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant7.0 GB
Quick answer

navarasa-malayalam-gguf needs about 11.3 GB of memory at Q6_K (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.0 GB (Q6_K) to 17.1 GB (BF16).

navarasa-malayalam-gguf is a 8.54B-parameter Gemma model in GGUF format, quantized by animaRegem. Its trained context length is 8K tokens. The repository has 2 quant files, from 7.0 GB (Q6_K) to 17.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K7.0 GB 11.3 GB
Too big Get file →
BF1617.1 GB 21.3 GB
Too big Get file →

What GPU do you need for navarasa-malayalam-gguf?

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 Q6_K (7.0 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 11.3 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.1 GB file, about 21.3 GB in use).

Which navarasa-malayalam-gguf quant should you choose?

Q6_K (7.0 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

Architecturegemma
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)448 KB per token

Source

Quantized byanimaRegem
FamilyGemma
Licenseapache-2.0
Downloads (HF)34
Last updated2024-07-05

Frequently asked questions about navarasa-malayalam-gguf

How much VRAM does navarasa-malayalam-gguf need?

About 11.3 GB at Q6_K with an 8K context window. That is the 7.0 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 navarasa-malayalam-gguf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of navarasa-malayalam-gguf GGUF?

It depends on the quant: Q6_K is 7.0 GB, BF16 is 17.1 GB.

What context length does navarasa-malayalam-gguf support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.

Where can I download navarasa-malayalam-gguf GGUF?

The files are on Hugging Face in the animaRegem/navarasa-malayalam-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 navarasa-malayalam-gguf 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.

Other GGUFs of Indic-gemma-7b-finetuned-sft-Navarasa-2.0

Similar models

Browse all →

More from animaRegem

All by animaRegem →

More Gemma models

All Gemma →

Other small models

All small models →