AU

Aura MoE 2x4B v2

AuraGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters7.23B
Context128K
Layers32
Architecturellama
Smallest quant1.8 GB
Quick answer

Aura MoE 2x4B v2 needs about 6.0 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 1.8 GB (IQ1_S) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Aura MoE 2x4B v2 – 7.23B parameter Mixture of Experts model

Aura MoE 2x4B v2 is a 7.23B parameter llama architecture model with mixture of experts. It supports roleplay and tools. The model was trained on a 131072 token context window and is released under the apache-2.0 license.

Good at

  • Roleplay
  • Tools usage
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Mixture of experts may increase latency

Best for

  • Chatbot development
  • Tool integration scenarios
  • Long-form content generation

Who it’s for. Developers building conversational agents that need roleplay or tool use capabilities. Researchers interested in Mixture of Experts models for large context tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.3 GB
Fits Get file →
IQ1_M1.9 GB 3.5 GB
Fits Get file →
IQ2_XXS2.1 GB 3.7 GB
Fits Get file →
IQ2_XS2.3 GB 3.9 GB
Fits Get file →
IQ2_S2.4 GB 4.0 GB
Fits Get file →
IQ2_M2.6 GB 4.2 GB
Fits Get file →
Q2_K_S2.7 GB 4.2 GB
Fits Get file →
Q2_K2.8 GB 4.4 GB
Fits Get file →
IQ3_XXS2.9 GB 4.5 GB
Fits Get file →
IQ3_XS3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.3 GB 4.8 GB
Fits Get file →
IQ3_S3.3 GB 4.9 GB
Fits Get file →
IQ3_M3.4 GB 4.9 GB
Fits Get file →
Q3_K_M3.6 GB 5.2 GB
Fits Get file →
Q3_K_L3.9 GB 5.4 GB
Fits Get file →
IQ4_XS4.0 GB 5.6 GB
Fits Get file →
Q4_04.2 GB 5.8 GB
Fits Get file →
Q4_K_S4.2 GB 5.8 GB
Fits Get file →
Q4_K_M4.4 GB 6.0 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.2 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (1.76 GB file, 3.3 GB memory) or IQ1_M (1.89 GB file, 3.5 GB memory). If more memory is available, Q4_K_M (4.42 GB file, 6 GB memory) offers higher quality. Memory estimates are approximate.

What GPU do you need for Aura MoE 2x4B v2?

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: the best quant that fits is IQ2_S (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).

Which Aura MoE 2x4B v2 quant should you choose?

Q4_K_M is the usual starting point for Aura MoE 2x4B v2: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is IQ1_S at 1.8 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
Parameters7.23B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyAura
Licenseapache-2.0
Downloads (HF)536
Last updated2024-12-16

Frequently asked questions about Aura MoE 2x4B v2

How much VRAM does Aura MoE 2x4B v2 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Aura MoE 2x4B v2 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Aura MoE 2x4B v2 GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.4 GB, IQ2_M is 2.6 GB and 16 more.

What context length does Aura MoE 2x4B v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Aura MoE 2x4B v2 GGUF?

The files are on Hugging Face in the mradermacher/Aura-MoE-2x4B-v2-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 Aura MoE 2x4B v2 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 Aura MoE 2x4B v2 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with estimated memory usage around 3.3–3.5 GB at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aura models

All Aura →

Other small models

All small models →