OB

obsidian 3b multimodal q6

ObsidianGGUF by nistenUpdated 2023-12-09
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant2.3 GB
Quick answer

obsidian 3b multimodal q6 needs about 5.5 GB of memory at its main file (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.3 GB to 5.6 GB (F16).

obsidian 3b multimodal q6 is a 2.8B-parameter Obsidian model in GGUF format, quantized by nisten. Its trained context length is 4K tokens. The repository has 2 quant files, from 2.3 GB to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.3 GB 4.1 GB
Fits Get file →
F165.6 GB 7.4 GB
Tight Get file →

What GPU do you need for obsidian 3b multimodal q6?

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 the main file (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (2.3 GB file, about 5.5 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bynisten
FamilyObsidian
Licensemit
Downloads (HF)189
Last updated2023-12-09

Frequently asked questions about obsidian 3b multimodal q6

How much VRAM does obsidian 3b multimodal q6 need?

About 5.5 GB at its main file with an 8K context window. That is the 2.3 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 obsidian 3b multimodal q6 on an 8 GB GPU?

Yes, with the smaller files: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of obsidian 3b multimodal q6 GGUF?

It depends on the quant: file is 2.3 GB, F16 is 5.6 GB.

What context length does obsidian 3b multimodal q6 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download obsidian 3b multimodal q6 GGUF?

The files are on Hugging Face in the nisten/obsidian-3b-multimodal-q6-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 obsidian 3b multimodal q6 use?

Hugging Face lists the license as mit. 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 nisten

All by nisten →

More Obsidian models

All Obsidian →

Other tiny models

All tiny models →