OB

Obsidian 3B V0.5

ObsidianGGUF by BlombertUpdated 2024-02-12
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant1.3 GB
Quick answer

Obsidian 3B V0.5 needs about 4.4 GB of memory at Q3_K_S (a 1.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.3 GB (Q3_K_S) to 5.6 GB (F16).

Obsidian 3B V0.5 is a 2.8B-parameter Obsidian model in GGUF format, quantized by Blombert. Its trained context length is 4K tokens. The repository has 2 quant files, from 1.3 GB (Q3_K_S) to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.3 GB 3.1 GB
Fits Get file →
F165.6 GB 7.4 GB
Tight Get file →

What GPU do you need for Obsidian 3B V0.5?

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 Q3_K_S (1.3 GB file, about 4.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_S (1.3 GB file, about 4.4 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Which Obsidian 3B V0.5 quant should you choose?

Q3_K_S (1.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byBlombert
FamilyObsidian
Downloads (HF)28
Last updated2024-02-12

Frequently asked questions about Obsidian 3B V0.5

How much VRAM does Obsidian 3B V0.5 need?

About 4.4 GB at Q3_K_S with an 8K context window. That is the 1.3 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 V0.5 on an 8 GB GPU?

Yes, with Q3_K_S: the 1.3 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Obsidian 3B V0.5 GGUF?

It depends on the quant: Q3_K_S is 1.3 GB, F16 is 5.6 GB.

What context length does Obsidian 3B V0.5 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 V0.5 GGUF?

The files are on Hugging Face in the Blombert/Obsidian-3B-V0.5-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Blombert

All by Blombert →

More Obsidian models

All Obsidian →

Other tiny models

All tiny models →