MO

model_merged_hindi_latest_16bit_q8_0

ModelGGUF by sanjay782Updated 2024-07-09
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant9.1 GB
Quick answer

model_merged_hindi_latest_16bit_q8_0 needs about 13.3 GB of memory at Q8_0 (a 9.1 GB file) with an 8K context window, so it fits on a 16 GB GPU.

model_merged_hindi_latest_16bit_q8_0 is a 8.54B-parameter Model model in GGUF format, quantized by sanjay782. Its trained context length is 8K tokens. The repository has 1 quant file, from 9.1 GB (Q8_0) to 9.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_09.1 GB 13.3 GB
Too big Get file →

What GPU do you need for model_merged_hindi_latest_16bit_q8_0?

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: the best quant that fits is Q8_0 (9.1 GB file, about 13.3 GB in use).

Which model_merged_hindi_latest_16bit_q8_0 quant should you choose?

Q8_0 (9.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 bysanjay782
FamilyModel
Licenseapache-2.0
Downloads (HF)11
Last updated2024-07-09

Frequently asked questions about model_merged_hindi_latest_16bit_q8_0

How much VRAM does model_merged_hindi_latest_16bit_q8_0 need?

About 13.3 GB at Q8_0 with an 8K context window. That is the 9.1 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 model_merged_hindi_latest_16bit_q8_0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of model_merged_hindi_latest_16bit_q8_0 GGUF?

It depends on the quant: Q8_0 is 9.1 GB.

What context length does model_merged_hindi_latest_16bit_q8_0 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 model_merged_hindi_latest_16bit_q8_0 GGUF?

The files are on Hugging Face in the sanjay782/model_merged_hindi_latest_16bit_q8_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does model_merged_hindi_latest_16bit_q8_0 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 model_merged_hindi_latest_16bit

Similar models

Browse all →

More from sanjay782

All by sanjay782 →

More Model models

All Model →

Other small models

All small models →