UM

Umbra-v3-MoE-4x11b-2ex

UmbraGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters36.1B
Context32K
Layers48
Architecturellama
Smallest quant7.4 GB
Quick answer

Umbra-v3-MoE-4x11b-2ex needs about 23.9 GB of memory at Q4_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.4 GB (IQ1_S) to 29.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Umbra‑v3‑MoE‑4x11b‑2ex – a 36.1B‑parameter Mixture of Experts LLM

Umbra‑v3‑MoE‑4x11b‑2ex is a 36.1B‑parameter model built on the Umbra family. It uses a mixture of experts architecture and was trained on a 32768‑token context window. The model is released under the apache‑2.0 license.

Good at

  • General assistance
  • Storytelling and RP/ERP
  • Multi‑source integration

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • Limited to 32768‑token context

Best for

  • Chatting with long context
  • Creative writing sessions
  • Role‑playing scenarios

Who it’s for. Developers and researchers who need a large, general‑purpose LLM with strong storytelling capabilities. The model is suitable for applications that can accommodate its memory requirements and do not require vision or multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.4 GB 9.6 GB
Too big Get file →
IQ1_M8.2 GB 10.3 GB
Too big Get file →
IQ2_XXS9.5 GB 11.6 GB
Too big Get file →
IQ2_XS10.6 GB 12.7 GB
Too big Get file →
IQ2_S10.9 GB 13.0 GB
Too big Get file →
IQ2_M11.9 GB 14.0 GB
Too big Get file →
Q2_K13.2 GB 15.3 GB
Too big Get file →
IQ3_XXS13.9 GB 16.0 GB
Too big Get file →
IQ3_XS14.8 GB 16.9 GB
Too big Get file →
Q3_K_S15.6 GB 17.7 GB
Too big Get file →
IQ3_S15.6 GB 17.7 GB
Too big Get file →
IQ3_M15.9 GB 18.0 GB
Too big Get file →
Q3_K_M17.3 GB 19.4 GB
Too big Get file →
Q3_K_L18.7 GB 20.8 GB
Too big Get file →
IQ4_XS19.3 GB 21.4 GB
Too big Get file →
Q4_020.4 GB 22.5 GB
Too big Get file →
Q4_K_S20.5 GB 22.6 GB
Too big Get file →
Q4_K_M21.8 GB 23.9 GB
Too big Get file →
Q5_K_S24.8 GB 27.0 GB
Too big Get file →
Q5_K_M25.6 GB 27.7 GB
Too big Get file →
Q6_K29.6 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.45 GB, 9.6 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (10.61 GB, 12.7 GB memory). For 24 GB VRAM, Q4_K_M (21.82 GB, 23.9 GB memory). Estimates are approximate.

What GPU do you need for Umbra-v3-MoE-4x11b-2ex?

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: the best quant that fits is IQ2_XXS (9.5 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.9 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.8 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.6 GB file, about 31.7 GB in use).

Which Umbra-v3-MoE-4x11b-2ex quant should you choose?

Q4_K_M is the usual starting point for Umbra-v3-MoE-4x11b-2ex: it balances file size and quality well. Here it is a 21.8 GB file.

If memory is tight, the smallest file is IQ1_S at 7.4 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
Parameters36.1B (approximate, mixture of experts)
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyUmbra
Licenseapache-2.0
Downloads (HF)4,066
Last updated2024-12-16

Frequently asked questions about Umbra-v3-MoE-4x11b-2ex

How much VRAM does Umbra-v3-MoE-4x11b-2ex need?

About 23.9 GB at Q4_K_M with an 8K context window. That is the 21.8 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 Umbra-v3-MoE-4x11b-2ex on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Umbra-v3-MoE-4x11b-2ex GGUF?

It depends on the quant: IQ1_S is 7.4 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.6 GB, IQ2_S is 10.9 GB, IQ2_M is 11.9 GB and 15 more.

What context length does Umbra-v3-MoE-4x11b-2ex support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Umbra-v3-MoE-4x11b-2ex GGUF?

The files are on Hugging Face in the mradermacher/Umbra-v3-MoE-4x11b-2ex-i1-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 Umbra-v3-MoE-4x11b-2ex 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 Umbra‑v3‑MoE‑4x11b‑2ex on 8 GB VRAM?

Use the IQ1_S quant, which is 7.45 GB and requires about 9.6 GB of VRAM at 8 k context.

Does this model support vision?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Umbra-v3-MoE-4x11b-2ex

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Umbra models

All Umbra →

Other large models

All large models →