AT

atlas models

AtlasGGUF by studiocatalystUpdated 2026-11-01
Download on Hugging Face
Parameters271M
Context256K
Layers24
Architecturegemma-embedding2
Smallest quant0.2 GB
Quick answer

atlas models needs about 2.3 GB of memory at Q5_K_XL (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q5_K_XL) to 1.5 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

atlas models is a 271M-parameter Atlas model in GGUF format, quantized by studiocatalyst. Its trained context length is 256K tokens. The repository has 2 quant files, from 0.2 GB (Q5_K_XL) to 1.5 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_XL0.2 GB 2.3 GB
Fits Get file →
Q5_K_M1.5 GB 3.6 GB
Fits Get file →

What GPU do you need for atlas models?

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 Q5_K_M (1.5 GB file, about 3.6 GB in use).

Which atlas models quant should you choose?

Q5_K_XL (0.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma-embedding2
Parameters271M
Layers24
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Source

Quantized bystudiocatalyst
FamilyAtlas
Licenseother
Downloads (HF)194
Last updated2026-11-01

Frequently asked questions about atlas models

How much VRAM does atlas models need?

About 2.3 GB at Q5_K_XL with an 8K context window. That is the 0.2 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 atlas models on an 8 GB GPU?

Yes, with Q5_K_M: the 1.5 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of atlas models GGUF?

It depends on the quant: Q5_K_XL is 0.2 GB, Q5_K_M is 1.5 GB.

What context length does atlas models support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download atlas models GGUF?

The files are on Hugging Face in the studiocatalyst/atlas-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does atlas models use?

Hugging Face lists the license as other. 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 Atlas models

All Atlas →

Other tiny models

All tiny models →