TR

Trixster MoE 14B A8B v1

TrixsterGGUF by mradermacherUpdated 2026-02-22
Download on Hugging Face
Parameters13.7B
Context1048K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Trixster MoE 14B A8B v1 needs about 9.9 GB of memory at Q4_K_M (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 11.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Trixster MoE 14B A8B v1 – 13.7B parameter LLaMA model with mixture of experts

Trixster MoE 14B A8B v1 is a 13.7B parameter LLaMA model that uses a mixture of experts with 8B active parameters. It was trained on 1,073,152 context tokens and supports roleplay and tools. The model is released under the apache-2.0 license.

Good at

  • Roleplay with mythic personas
  • Tool usage in prompts
  • Mixture of experts for efficient inference

Limits

  • No vision support
  • Requires large VRAM for higher quant levels
  • License is apache-2.0

Best for

  • Interactive storytelling
  • Prompt engineering with tools
  • Research on MoE architectures

Who it’s for. Developers and researchers who need a large LLaMA model with mixture of experts and roleplay capabilities. The model is suitable for applications that can handle its memory requirements and do not require vision or other modalities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S3.2 GB 4.7 GB
Fits Get file →
IQ1_M3.4 GB 5.0 GB
Fits Get file →
IQ2_XXS3.9 GB 5.4 GB
Fits Get file →
IQ2_XS4.2 GB 5.8 GB
Fits Get file →
IQ2_S4.4 GB 6.0 GB
Fits Get file →
IQ2_M4.8 GB 6.4 GB
Fits Get file →
Q2_K_S4.9 GB 6.5 GB
Fits Get file →
Q2_K5.2 GB 6.8 GB
Fits Get file →
IQ3_XXS5.4 GB 7.0 GB
Fits Get file →
IQ3_XS5.8 GB 7.4 GB
Tight Get file →
Q3_K_S6.1 GB 7.7 GB
Tight Get file →
IQ3_S6.1 GB 7.7 GB
Tight Get file →
IQ3_M6.2 GB 7.8 GB
Tight Get file →
Q3_K_M6.7 GB 8.3 GB
Too big Get file →
Q3_K_L7.2 GB 8.8 GB
Too big Get file →
IQ4_XS7.4 GB 9.0 GB
Too big Get file →
IQ4_NL7.9 GB 9.4 GB
Too big Get file →
Q4_07.9 GB 9.4 GB
Too big Get file →
Q4_K_S7.9 GB 9.5 GB
Too big Get file →
Q4_K_M8.3 GB 9.9 GB
Too big Get file →
Q4_18.7 GB 10.2 GB
Too big Get file →
Q5_K_S9.5 GB 11.0 GB
Too big Get file →
Q5_K_M9.7 GB 11.3 GB
Too big Get file →
Q6_K11.2 GB 12.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 8.33 GB, estimated memory 9.9 GB). For 12 GB VRAM, Q5_K_M (9.73 GB, 11.3 GB). For 16 GB VRAM, Q6_K (11.22 GB, 12.8 GB). Smaller quants such as IQ1_S or IQ1_M are also available for lower memory budgets.

What GPU do you need for Trixster MoE 14B A8B v1?

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 the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ2_S (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.7 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 12.8 GB in use).

Which Trixster MoE 14B A8B v1 quant should you choose?

Q4_K_M is the usual starting point for Trixster MoE 14B A8B v1: it balances file size and quality well. Here it is a 8.3 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.7B (approximate, mixture of experts)
Active parameters8B
Layers32
Trained context1,073,152 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyTrixster
Licenseapache-2.0
Downloads (HF)538
Last updated2026-02-22

Frequently asked questions about Trixster MoE 14B A8B v1

How much VRAM does Trixster MoE 14B A8B v1 need?

About 9.9 GB at Q4_K_M with an 8K context window. That is the 8.3 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 Trixster MoE 14B A8B v1 on an 8 GB GPU?

Yes, with IQ3_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 Trixster MoE 14B A8B v1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.2 GB, IQ1_M is 3.4 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.4 GB and 19 more.

What context length does Trixster MoE 14B A8B v1 support?

The GGUF header lists a trained context length of 1,073,152 tokens (1048K). 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 Trixster MoE 14B A8B v1 GGUF?

The files are on Hugging Face in the mradermacher/Trixster-MoE-14B-A8B-v1-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 Trixster MoE 14B A8B v1 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?

Use the Q4_K_M quant which requires about 9.9 GB of VRAM. It may fit with memory optimizations but is close to the limit.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Trixster-MoE-14B-A8B-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Trixster models

All Trixster →

Other medium models

All medium models →