VI

Viloet Eclipse 2x12B v0.2 MINI

ViloetGGUF by SuperbEmphasisUpdated 2025-06-14
Download on Hugging Face
Parameters21.1B
Context1000K
Layers40
Architecturellama
Smallest quant17.3 GB
Quick answer

Viloet Eclipse 2x12B v0.2 MINI needs about 19.1 GB of memory at Q6_K (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Viloet Eclipse 2x12B v0.2 MINI is a 21.1B-parameter Viloet model in GGUF format, quantized by SuperbEmphasis. Its trained context length is 1000K tokens. The repository has 1 quant file, from 17.3 GB (Q6_K) to 17.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K17.3 GB 19.1 GB
Too big Get file →

What GPU do you need for Viloet Eclipse 2x12B v0.2 MINI?

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 Q6_K (17.3 GB file, about 19.1 GB in use).

Which Viloet Eclipse 2x12B v0.2 MINI quant should you choose?

Q6_K (17.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters21.1B (approximate, mixture of experts)
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bySuperbEmphasis
FamilyViloet
Downloads (HF)14
Last updated2025-06-14

Frequently asked questions about Viloet Eclipse 2x12B v0.2 MINI

How much VRAM does Viloet Eclipse 2x12B v0.2 MINI need?

About 19.1 GB at Q6_K with an 8K context window. That is the 17.3 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 Viloet Eclipse 2x12B v0.2 MINI on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Viloet Eclipse 2x12B v0.2 MINI GGUF?

It depends on the quant: Q6_K is 17.3 GB.

What context length does Viloet Eclipse 2x12B v0.2 MINI support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). 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 Viloet Eclipse 2x12B v0.2 MINI GGUF?

The files are on Hugging Face in the SuperbEmphasis/Viloet-Eclipse-2x12B-v0.2-MINI-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Viloet-Eclipse-2x12B-v0.2-MINI

Similar models

Browse all →

More from SuperbEmphasis

All by SuperbEmphasis →

More Viloet models

All Viloet →

Other medium models

All medium models →