VE

Velvet Eclipse v0.1 3x12B MoE

VelvetGGUF by SuperbEmphasisUpdated 2025-04-15
Download on Hugging Face
Parameters29.9B
Context128K
Layers40
Architecturellama
Smallest quant18.1 GB
Quick answer

Velvet Eclipse v0.1 3x12B MoE needs about 20.0 GB of memory at Q4_K_M (a 18.1 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.

Velvet Eclipse v0.1 3x12B MoE is a 29.9B-parameter Velvet model in GGUF format, quantized by SuperbEmphasis. Its trained context length is 128K tokens. The repository has 1 quant file, from 18.1 GB (Q4_K_M) to 18.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.1 GB 20.0 GB
Too big Get file →

What GPU do you need for Velvet Eclipse v0.1 3x12B MoE?

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_M (18.1 GB file, about 20.0 GB in use).

Which Velvet Eclipse v0.1 3x12B MoE quant should you choose?

Q4_K_M is the usual starting point for Velvet Eclipse v0.1 3x12B MoE: it balances file size and quality well. Here it is a 18.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters29.9B (approximate, mixture of experts)
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bySuperbEmphasis
FamilyVelvet
Licenseapache-2.0
Downloads (HF)4
Last updated2025-04-15

Frequently asked questions about Velvet Eclipse v0.1 3x12B MoE

How much VRAM does Velvet Eclipse v0.1 3x12B MoE need?

About 20.0 GB at Q4_K_M with an 8K context window. That is the 18.1 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 Velvet Eclipse v0.1 3x12B MoE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Velvet Eclipse v0.1 3x12B MoE GGUF?

It depends on the quant: Q4_K_M is 18.1 GB.

What context length does Velvet Eclipse v0.1 3x12B MoE 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 Velvet Eclipse v0.1 3x12B MoE GGUF?

The files are on Hugging Face in the SuperbEmphasis/Velvet-Eclipse-v0.1-3x12B-MoE-Q4_K_M-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 Velvet Eclipse v0.1 3x12B MoE 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 SuperbEmphasis

All by SuperbEmphasis →

More Velvet models

All Velvet →

Other medium models

All medium models →