AT

Atom v1 Preview 12b

AtomGGUF by mradermacherUpdated 2026-03-12
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Atom v1 Preview 12b needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 9.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Atom v1 Preview 12b – 12B Gemma3 conversational model

Atom v1 Preview 12b is a 12 billion parameter Gemma3 model fine‑tuned for collaborative dialogue. It supports long‑context processing with a 131,072 token window. The model is released under the Gemma license.

Good at

  • Collaborative brainstorming
  • Research synthesis
  • Technical explanation

Limits

  • No vision support in this GGUF release
  • Large VRAM requirement for higher quants
  • License restricts commercial use

Best for

  • Idea generation sessions
  • Academic literature reviews
  • Code discussion and debugging

Who it’s for. Developers, researchers, and writers who need a conversational partner for exploration and problem solving. The model is suitable for users with access to sufficient GPU memory to run the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.7 GB
Fits Get file →
IQ1_S2.9 GB 6.7 GB
Fits Get file →
IQ1_M3.2 GB 6.9 GB
Fits Get file →
IQ2_XXS3.5 GB 7.2 GB
Tight Get file →
IQ2_XS3.8 GB 7.6 GB
Tight Get file →
IQ2_S4.0 GB 7.7 GB
Tight Get file →
IQ2_M4.3 GB 8.0 GB
Too big Get file →
Q2_K_S4.4 GB 8.2 GB
Too big Get file →
Q2_K4.8 GB 8.5 GB
Too big Get file →
IQ3_XXS4.8 GB 8.5 GB
Too big Get file →
IQ3_XS5.2 GB 8.9 GB
Too big Get file →
IQ3_S5.5 GB 9.2 GB
Too big Get file →
Q3_K_S5.5 GB 9.2 GB
Too big Get file →
IQ3_M5.7 GB 9.4 GB
Too big Get file →
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q3_K_L6.5 GB 10.2 GB
Too big Get file →
IQ4_XS6.6 GB 10.3 GB
Too big Get file →
IQ4_NL6.9 GB 10.6 GB
Too big Get file →
Q4_06.9 GB 10.6 GB
Too big Get file →
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q4_17.6 GB 11.3 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.95 GB file, 6.7 GB memory). With 12 GB VRAM, IQ4_0 (6.91 GB file, 10.6 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (8.45 GB file, 12.2 GB memory) offers higher quality.

What GPU do you need for Atom v1 Preview 12b?

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 the main file (0.0 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_M (4.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).

Which Atom v1 Preview 12b quant should you choose?

Q4_K_M is the usual starting point for Atom v1 Preview 12b: it balances file size and quality well. Here it is a 7.3 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyAtom
Licensegemma
Downloads (HF)1,021
Last updated2026-03-12

Frequently asked questions about Atom v1 Preview 12b

How much VRAM does Atom v1 Preview 12b need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 Atom v1 Preview 12b on an 8 GB GPU?

Yes, with IQ2_M: the 4.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Atom v1 Preview 12b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.9 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB and 19 more.

What context length does Atom v1 Preview 12b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Atom v1 Preview 12b GGUF?

The files are on Hugging Face in the mradermacher/atom-v1-preview-12b-i1-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 Atom v1 Preview 12b use?

Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Atom v1 Preview 12b on 8 GB VRAM?

Yes, the IQ1_S quant uses 6.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision?

The GGUF release does not include vision files; it is text‑only.

What license applies to this model?

The model is released under the Gemma Terms of Use, which limits commercial use.

Other GGUFs of atom-v1-preview-12b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Atom models

All Atom →

Other medium models

All medium models →