AT

Atlas Code

AtlasGGUF by archwayaiUpdated 2026-03-27
Download on Hugging Face
Parameters25.9B
Context256K
Layers36
Architectureqwen3moe
Smallest quant14.8 GB
Quick answer

Atlas Code needs about 29.3 GB of memory at Q8_0 (a 27.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 14.8 GB (Q4_K_S) to 51.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Atlas Code is a 25.9B-parameter Atlas model in GGUF format, quantized by archwayai. Its trained context length is 256K tokens. The repository has 3 quant files, from 14.8 GB (Q4_K_S) to 51.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S14.8 GB 16.5 GB
Too big Get file →
Q8_027.6 GB 29.3 GB
Too big Get file →
F1651.9 GB 53.6 GB
Too big Get file →

What GPU do you need for Atlas Code?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_S (14.8 GB file, about 16.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (27.6 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (27.6 GB file, about 29.3 GB in use).

Which Atlas Code quant should you choose?

Q8_0 (27.6 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.

If memory is tight, the smallest file is Q4_K_S at 14.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters25.9B (approximate, mixture of experts)
Active parameters4B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byarchwayai
FamilyAtlas
Licenseapache-2.0
Downloads (HF)26
Last updated2026-03-27

Frequently asked questions about Atlas Code

How much VRAM does Atlas Code need?

About 29.3 GB at Q8_0 with an 8K context window. That is the 27.6 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 Code on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Atlas Code GGUF?

It depends on the quant: Q4_K_S is 14.8 GB, Q8_0 is 27.6 GB, F16 is 51.9 GB.

What context length does Atlas Code support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Atlas Code GGUF?

The files are on Hugging Face in the archwayai/Atlas_Code_26B-A4B 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 Code use?

Hugging Face lists the license as apache-2.0. 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 archwayai

All by archwayai →

More Atlas models

All Atlas →

Other medium models

All medium models →