TI

TinyDolphin 2.8.2 1.1b laser

TinydolphinGGUF by invalid-coderUpdated 2024-03-20
Download on Hugging Face
Parameters1.1B
Context4K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

TinyDolphin 2.8.2 1.1b laser needs about 4.8 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 0.0 GB to 0.7 GB (Q4_K).

TinyDolphin 2.8.2 1.1b laser is a 1.1B-parameter Tinydolphin model in GGUF format, quantized by invalid-coder. Its trained context length is 4K tokens. The repository has 2 quant files, from 0.0 GB to 0.7 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.6 GB
Fits Get file →
Q4_K0.7 GB 3.3 GB
Fits Get file →

What GPU do you need for TinyDolphin 2.8.2 1.1b laser?

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 Q4_K (0.7 GB file, about 5.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.1B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byinvalid-coder
Downloads (HF)63
Last updated2024-03-20

Frequently asked questions about TinyDolphin 2.8.2 1.1b laser

How much VRAM does TinyDolphin 2.8.2 1.1b laser need?

About 4.8 GB at its main file with an 8K context window. That is the 0.0 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 TinyDolphin 2.8.2 1.1b laser on an 8 GB GPU?

Yes, with Q4_K: the 0.7 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 TinyDolphin 2.8.2 1.1b laser GGUF?

It depends on the quant: file is 0.0 GB, Q4_K is 0.7 GB.

What context length does TinyDolphin 2.8.2 1.1b laser support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download TinyDolphin 2.8.2 1.1b laser GGUF?

The files are on Hugging Face in the invalid-coder/TinyDolphin-2.8.2-1.1b-laser-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 invalid-coder

All by invalid-coder →

More Tinydolphin models

All Tinydolphin →

Other tiny models

All tiny models →