AL

Algae 550M Base

AlgaeGGUF by mradermacherUpdated 2024-11-07
Download on Hugging Face
Parameters555M
Context1K
Layers25
Architecturephi2
Smallest quant0.2 GB
Quick answer

Algae 550M Base needs about 1.9 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.2 GB (Q2_K) to 1.1 GB (F16).

Algae 550M Base is a 555M-parameter Algae model in GGUF format, quantized by mradermacher. Its trained context length is 1K tokens. The repository has 13 quant files, from 0.2 GB (Q2_K) to 1.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 0.9 GB
Fits Get file →
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
Q3_K_M0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.3 GB 1.0 GB
Fits Get file →
Q3_K_L0.3 GB 1.0 GB
Fits Get file →
Q4_00.3 GB 1.0 GB
Fits Get file →
Q4_K_S0.3 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.6 GB 1.2 GB
Fits Get file →
F161.1 GB 1.7 GB
Fits Get file →

What GPU do you need for Algae 550M Base?

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 F16 (1.1 GB file, about 2.7 GB in use).

Which Algae 550M Base quant should you choose?

Q4_K_M is the usual starting point for Algae 550M Base: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters555M
Layers25
Trained context1,024 tokens
KV cache (fp16)125 KB per token

Source

Quantized bymradermacher
FamilyAlgae
Licensemit
Downloads (HF)155
Last updated2024-11-07

Frequently asked questions about Algae 550M Base

How much VRAM does Algae 550M Base need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.4 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 Algae 550M Base on an 8 GB GPU?

Yes, with F16: the 1.1 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Algae 550M Base GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.3 GB, IQ4_XS is 0.3 GB, Q3_K_L is 0.3 GB, Q4_0 is 0.3 GB and 7 more.

What context length does Algae 550M Base support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 1.0 GB at 8K and 0.1 GB at 1K.

Where can I download Algae 550M Base GGUF?

The files are on Hugging Face in the mradermacher/Algae-550M-base-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 Algae 550M Base 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 mradermacher

All by mradermacher →

More Algae models

All Algae →

Other tiny models

All tiny models →