RO

Rocinante X 12B v1 Absolute Heresy

RocinanteGGUF by daniel8757Updated 2026-03-18
Download on Hugging Face
Parameters12.2B
Context128K
Layers40
Architecturellama
Smallest quant3.6 GB
Quick answer

Rocinante X 12B v1 Absolute Heresy needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 3.6 GB (IQ2_XXS) to 10.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Rocinante X 12B v1 Absolute Heresy is a 12.2B-parameter Rocinante model in GGUF format, quantized by daniel8757. Its trained context length is 128K tokens. The repository has 3 quant files, from 3.6 GB (IQ2_XXS) to 10.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS3.6 GB 5.4 GB
Fits Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →

What GPU do you need for Rocinante X 12B v1 Absolute Heresy?

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: the best quant that fits is IQ2_XXS (3.6 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (3.6 GB file, about 5.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).

Which Rocinante X 12B v1 Absolute Heresy quant should you choose?

Q4_K_M is the usual starting point for Rocinante X 12B v1 Absolute Heresy: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is IQ2_XXS at 3.6 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

Architecturellama
Parameters12.2B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Frequently asked questions about Rocinante X 12B v1 Absolute Heresy

How much VRAM does Rocinante X 12B v1 Absolute Heresy need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Rocinante X 12B v1 Absolute Heresy on an 8 GB GPU?

Yes, with IQ2_XXS: the 3.6 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Rocinante X 12B v1 Absolute Heresy GGUF?

It depends on the quant: IQ2_XXS is 3.6 GB, Q4_K_M is 7.5 GB, Q6_K is 10.1 GB.

What context length does Rocinante X 12B v1 Absolute Heresy support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Rocinante X 12B v1 Absolute Heresy GGUF?

The files are on Hugging Face in the daniel8757/MuXodious-Rocinante-X-12B-v1-absolute-heresy-SDPL-Experiment-i-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 Rocinante X 12B v1 Absolute Heresy 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.

Other GGUFs of Rocinante-X-12B-v1-absolute-heresy

Similar models

Browse all →

More Rocinante models

All Rocinante →

Other medium models

All medium models →