SH

Shadow Siren 14B Pruned

ShadowGGUF by mradermacherUpdated 2026-10-04
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant10.6 GB
Quick answer

Shadow Siren 14B Pruned needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 10.6 GB (Q2_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Shadow Siren 14B Pruned – a 25.2B‑parameter gemma4 model with vision and roleplay abilities

Shadow Siren 14B Pruned is a surgically pruned 64‑expert variant of the Shadow family. It retains the original chat templates and tokenizer metadata for persistent multi‑turn reasoning. The model is released under the Apache‑2.0 license.

Good at

  • Vision‑enabled roleplay
  • Persistent multi‑turn reasoning
  • Surgically pruned MoE architecture

Limits

  • Requires large VRAM – 19.1 GB at 8 k context for Q2_K
  • No external vision support beyond built‑in
  • License allows free use but no redistribution of weights

Best for

  • Local vision‑enabled chatbots
  • Fine‑tuning with custom quantization
  • Research on MoE pruning techniques

Who it’s for. Developers and researchers who need a vision‑capable LLM with a reduced expert set for faster inference. The model is suitable for local deployment on machines with sufficient VRAM and for fine‑tuning workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.6 GB 19.1 GB
Too big Get file →
Q3_K_S12.2 GB 20.8 GB
Too big Get file →
Q3_K_M13.3 GB 21.8 GB
Too big Get file →
Q3_K_L13.8 GB 22.4 GB
Too big Get file →
IQ4_XS14.1 GB 22.6 GB
Too big Get file →
Q4_K_S15.5 GB 24.0 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_S18.0 GB 26.5 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →

For 8 GB VRAM, the smallest quant is Q2_K at 10.58 GB, but it still needs about 19.1 GB of VRAM at 8 k context, so it is not feasible. A more realistic choice for 8 GB VRAM is Q4_K_S (15.46 GB) which requires roughly 24 GB of VRAM. For higher memory budgets, Q6_K or Q8_0 provide better quality.

What GPU do you need for Shadow Siren 14B Pruned?

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_S (15.5 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which Shadow Siren 14B Pruned quant should you choose?

Q4_K_M is the usual starting point for Shadow Siren 14B Pruned: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 GB, about 1.6 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 10.6 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

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyShadow
Licenseapache-2.0
Downloads (HF)230
Last updated2026-10-04

Frequently asked questions about Shadow Siren 14B Pruned

How much VRAM does Shadow Siren 14B Pruned need?

About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Shadow Siren 14B Pruned 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 Shadow Siren 14B Pruned GGUF?

It depends on the quant: Q2_K is 10.6 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.3 GB, Q3_K_L is 13.8 GB, IQ4_XS is 14.1 GB, Q4_K_S is 15.5 GB and 5 more.

What context length does Shadow Siren 14B Pruned support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Shadow Siren 14B Pruned GGUF?

The files are on Hugging Face in the mradermacher/Shadow-Siren-14B-Pruned-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 Shadow Siren 14B Pruned 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.

Can I run Shadow Siren 14B Pruned on 8 GB VRAM?

No. Even the smallest quant (Q2_K) requires about 19.1 GB of VRAM at 8 k context. 8 GB is insufficient for any quant of this model.

Does Shadow Siren 14B Pruned support vision?

Yes. The model has detected vision abilities and can process image inputs.

Other GGUFs of Shadow-Siren-14B-Pruned

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shadow models

All Shadow →

Other medium models

All medium models →