SH

Shadows-MoE

ShadowsGGUF by mradermacherUpdated 2024-07-04
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

Shadows-MoE needs about 9.4 GB of memory at Q4_K_M (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.8 GB (Q2_K) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Shadows-MoE: 12.9B llama-based MoE model in GGUF format

Shadows-MoE is a 12.9B parameter llama architecture model that uses a mixture of experts. It was trained on 32768 context tokens and is available in multiple static quantizations. The model is hosted on the mradermacher Hugging Face repository.

Good at

  • Large context handling
  • Mixture of experts architecture
  • Multiple quant options

Limits

  • No license specified
  • No vision support
  • Requires 8k context for memory estimates

Best for

  • Chat applications
  • Long‑form content generation
  • Research prototyping

Who it’s for. Developers and researchers who need a llama-based MoE model with flexible quantization. The model is suitable for local deployment using llama.cpp and GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.3 GB
Fits Get file →
IQ3_XS5.3 GB 6.9 GB
Fits Get file →
Q3_K_S5.6 GB 7.2 GB
Fits Get file →
IQ3_S5.6 GB 7.2 GB
Fits Get file →
IQ3_M5.7 GB 7.3 GB
Tight Get file →
Q3_K_M6.2 GB 7.8 GB
Tight Get file →
Q3_K_L6.7 GB 8.3 GB
Too big Get file →
IQ4_XS7.0 GB 8.6 GB
Too big Get file →
Q4_K_S7.3 GB 8.9 GB
Too big Get file →
Q4_K_M7.8 GB 9.4 GB
Too big Get file →
Q5_K_S8.9 GB 10.4 GB
Too big Get file →
Q5_K_M9.1 GB 10.7 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →
Q8_013.7 GB 15.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 7.34 GB, estimated memory 8.9 GB). For 12 GB VRAM, Q5_K_M (file size 9.13 GB, estimated memory 10.7 GB) is a good balance. For 16 GB VRAM, Q6_K (file size 10.57 GB, estimated memory 12.1 GB) provides higher quality.

What GPU do you need for Shadows-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: the best quant that fits is Q3_K_M (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).

Which Shadows-MoE quant should you choose?

Q4_K_M is the usual starting point for Shadows-MoE: it balances file size and quality well. Here it is a 7.8 GB file.

The Q8_0 file is 13.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 4.8 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
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyShadows
Downloads (HF)1,081
Last updated2024-07-04

Frequently asked questions about Shadows-MoE

How much VRAM does Shadows-MoE need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 7.8 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 Shadows-MoE on an 8 GB GPU?

Yes, with Q3_K_M: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Shadows-MoE GGUF?

It depends on the quant: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.6 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.2 GB and 8 more.

What context length does Shadows-MoE support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Shadows-MoE GGUF?

The files are on Hugging Face in the mradermacher/Shadows-MoE-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Shadows-MoE on 8 GB VRAM?

Yes, the Q4_K_S quantization requires about 8.9 GB of memory at 8k context, which fits within 8 GB VRAM with some overhead.

Does Shadows-MoE support vision tasks?

No, the model does not include vision capabilities.

Where can I find the quantized GGUF files?

They are available on the mradermacher Hugging Face repository under the Shadows-MoE-GGUF folder.

Other GGUFs of Shadows-MoE

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shadows models

All Shadows →

Other medium models

All medium models →