QW

TroyDoesAIQwen3 15B A2B Base

QwenGGUF by Trilogix1Updated 2025-11-21
Download on Hugging Face
Parameters15.6B
Context4K
Layers24
Architectureqwen3moe
Smallest quant8.9 GB
Quick answer

TroyDoesAIQwen3 15B A2B Base needs about 12.0 GB of memory at F32 (a 11.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 8.9 GB (F32) to 31.2 GB (F32).

TroyDoesAIQwen3 15B A2B Base is a 15.6B-parameter Qwen model in GGUF format, quantized by Trilogix1. Its trained context length is 4K tokens. The repository has 6 quant files, from 8.9 GB (F32) to 31.2 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F328.9 GB 9.7 GB
Too big Get file →
F329.5 GB 10.2 GB
Too big Get file →
F3211.1 GB 11.8 GB
Too big Get file →
F3212.8 GB 13.5 GB
Too big Get file →
F3216.6 GB 17.3 GB
Too big Get file →
F3231.2 GB 31.9 GB
Too big Get file →

What GPU do you need for TroyDoesAIQwen3 15B A2B Base?

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 F32 (11.1 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is F32 (12.8 GB file, about 13.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (16.6 GB file, about 17.5 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (16.6 GB file, about 17.5 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (31.2 GB file, about 32.1 GB in use).

Which TroyDoesAIQwen3 15B A2B Base quant should you choose?

F32 (11.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F32 at 8.9 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters15.6B (approximate, mixture of experts)
Active parameters2B
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized byTrilogix1
FamilyQwen
Licenseapache-2.0
Downloads (HF)130
Last updated2025-11-21

Frequently asked questions about TroyDoesAIQwen3 15B A2B Base

How much VRAM does TroyDoesAIQwen3 15B A2B Base need?

About 12.0 GB at F32 with an 8K context window. That is the 11.1 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 TroyDoesAIQwen3 15B A2B Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TroyDoesAIQwen3 15B A2B Base GGUF?

It depends on the quant: F32 is 8.9 GB, F32 is 9.5 GB, F32 is 11.1 GB, F32 is 12.8 GB, F32 is 16.6 GB, F32 is 31.2 GB.

What context length does TroyDoesAIQwen3 15B A2B Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download TroyDoesAIQwen3 15B A2B Base GGUF?

The files are on Hugging Face in the Trilogix1/Hugston-TroyDoesAI-Qwen3-15B-A2B-Base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does TroyDoesAIQwen3 15B A2B Base 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.

Similar models

Browse all →

More from Trilogix1

All by Trilogix1 →

More Qwen models

All Qwen →

Other medium models

All medium models →