UM

Umbra-v3-MoE-4x11b-2ex

UmbraGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters36.1B
Context32K
Layers48
Architecturellama
Smallest quant13.2 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 14 quants, from 13.2 GB (Q2_K) to 38.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Umbra‑v3‑MoE‑4x11b‑2ex: 36.1B‑parameter Mixture of Experts LLaMA model

Umbra‑v3‑MoE‑4x11b‑2ex is a 36.1B‑parameter LLaMA‑based Mixture of Experts model. It supports a 32,768‑token context window and is licensed under Apache‑2.0. The model is tailored for general assistance and storytelling.

Good at

  • General assistance
  • Storytelling and RP/ERP
  • Large context handling

Limits

  • No vision support
  • Requires 32,768‑token context
  • Apache‑2.0 license

Best for

  • Chatbots needing long context
  • Creative writing assistants
  • Role‑playing game narrators

Who it’s for. Developers and hobbyists building chat or creative writing applications who need a large‑context LLaMA model. The model is free to use under Apache‑2.0 and can be run with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.2 GB 15.3 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_XS19.5 GB 21.6 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 →
Q8_038.4 GB 40.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (13.19 GB, ~15.3 GB memory at 8k context). For 12 GB VRAM, Q3_K_S (15.57 GB, ~17.7 GB memory). For 16 GB VRAM, Q4_K_M (21.82 GB, ~23.9 GB memory).

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (13.2 GB file, about 15.3 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).
  • 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 40.5 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.

The Q8_0 file is 38.4 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 13.2 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)1,317
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 15.3 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: Q2_K is 13.2 GB, IQ3_XS is 14.8 GB, Q3_K_S is 15.6 GB, IQ3_S is 15.6 GB, IQ3_M is 15.9 GB, Q3_K_M is 17.3 GB and 8 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-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 this model on 8 GB VRAM?

Yes, the Q2_K quant is 13.19 GB and requires about 15.3 GB of VRAM at 8k context.

Does the model support image inputs?

No, the model has no vision support.

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 →