SI

silma ai 9B instruct v1 q8

SilmaGGUF by tsharisaravananUpdated 2025-01-17
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant6.0 GB
Quick answer

silma ai 9B instruct v1 q8 needs about 9.3 GB of memory at its main file (a 6.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

silma ai 9B instruct v1 q8 is a 9.24B-parameter Silma model in GGUF format, quantized by tsharisaravanan. Its trained context length is 8K tokens. The repository has 1 quant file, from 6.0 GB to 6.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.0 GB 9.3 GB
Too big Get file →

What GPU do you need for silma ai 9B instruct v1 q8?

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 the main file (6.0 GB file, about 9.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma2
Parameters9.24B
Layers42
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bytsharisaravanan
FamilySilma
Licensegemma
Downloads (HF)6
Last updated2025-01-17

Frequently asked questions about silma ai 9B instruct v1 q8

How much VRAM does silma ai 9B instruct v1 q8 need?

About 9.3 GB at its main file with an 8K context window. That is the 6.0 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 silma ai 9B instruct v1 q8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of silma ai 9B instruct v1 q8 GGUF?

It depends on the quant: file is 6.0 GB.

What context length does silma ai 9B instruct v1 q8 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download silma ai 9B instruct v1 q8 GGUF?

The files are on Hugging Face in the tsharisaravanan/silma-ai-9B-instruct-v1-q8-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 silma ai 9B instruct v1 q8 use?

Hugging Face lists the license as gemma. 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 Silma models

All Silma →

Other small models

All small models →