CO

cosmo merge 1b v0.1

CosmoalpacalightGGUF by LambentUpdated 2024-03-07
Download on Hugging Face
Parameters1.74B
Context2K
Layers24
Architecturellama
Smallest quant1.9 GB
Quick answer

cosmo merge 1b v0.1 needs about 4.0 GB of memory at Q8_0 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU.

cosmo merge 1b v0.1 is a 1.74B-parameter Cosmoalpacalight model in GGUF format, quantized by Lambent. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.9 GB (Q8_0) to 1.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.9 GB 2.8 GB
Fits Get file →

What GPU do you need for cosmo merge 1b v0.1?

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: the best quant that fits is Q8_0 (1.9 GB file, about 4.0 GB in use).

Which cosmo merge 1b v0.1 quant should you choose?

Q8_0 (1.9 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

Architecturellama
Parameters1.74B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized byLambent
Downloads (HF)35
Last updated2024-03-07

Frequently asked questions about cosmo merge 1b v0.1

How much VRAM does cosmo merge 1b v0.1 need?

About 4.0 GB at Q8_0 with an 8K context window. That is the 1.9 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 cosmo merge 1b v0.1 on an 8 GB GPU?

Yes, with Q8_0: the 1.9 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cosmo merge 1b v0.1 GGUF?

It depends on the quant: Q8_0 is 1.9 GB.

What context length does cosmo merge 1b v0.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download cosmo merge 1b v0.1 GGUF?

The files are on Hugging Face in the Lambent/cosmo-merge-1b-v0.1 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 Lambent

All by Lambent →

Other tiny models

All tiny models →