QW

Boogu Text Encoder Heretic DHQ

QwenGGUF by pottokaoUpdated 2026-10-17
Download on Hugging Face
Parameters8.19B
Context256K
Layers36
Architectureqwen3vl
Smallest quant2.9 GB
Quick answer

Boogu Text Encoder Heretic DHQ needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 2.9 GB (IQ2_S) to 5.0 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Boogu Text Encoder Heretic DHQ – 8.19B Qwen3-VL text encoder for diffusion models

Boogu Text Encoder Heretic DHQ is an 8.19B parameter Qwen3-VL text encoder derived from Qwen-Image-2.1. It is quantized with Dual‑Head Quantization for use as a diffusion model text encoder. The model is released under Apache‑2.0 and supports coding, tools, and vision.

Good at

  • Vision‑enabled text encoding
  • Diffusion model prompt enhancement
  • Low‑refusal behavior

Limits

  • No next‑token generation
  • No vision inference in isolation
  • Requires ComfyUI 0.36.0 or newer

Best for

  • Boogu DiT text conditioning
  • Prompt rewriting for diffusion models
  • Low‑latency inference on GPUs

Who it’s for. Developers building diffusion pipelines that need a Qwen3‑VL text encoder with reduced refusal behavior. The model is suitable for users who work with Boogu DiT or similar diffusion models and require a lightweight, quantized text encoder.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S2.9 GB 4.6 GB
Fits Get file →
Q2_K3.3 GB 5.0 GB
Fits Get file →
IQ3_S3.8 GB 5.5 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
Q3_K_M4.1 GB 5.8 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 5.03 GB, estimated 6.7 GB at 8 k context). For 4 GB VRAM, use IQ2_S (file size 2.86 GB, estimated 4.6 GB). For the smallest memory footprint, use IQ2_S or Q2_K, but note higher quantization error.

What GPU do you need for Boogu Text Encoder Heretic DHQ?

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: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.0 GB file, about 6.7 GB in use).

Which Boogu Text Encoder Heretic DHQ quant should you choose?

Q4_K_M is the usual starting point for Boogu Text Encoder Heretic DHQ: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is IQ2_S at 2.9 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

Architectureqwen3vl
Parameters8.19B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bypottokao
FamilyQwen
Licenseapache-2.0
Downloads (HF)693
Last updated2026-10-17

Frequently asked questions about Boogu Text Encoder Heretic DHQ

How much VRAM does Boogu Text Encoder Heretic DHQ need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Boogu Text Encoder Heretic DHQ on an 8 GB GPU?

Yes, with Q4_K_M: the 5.0 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Boogu Text Encoder Heretic DHQ GGUF?

It depends on the quant: IQ2_S is 2.9 GB, Q2_K is 3.3 GB, IQ3_S is 3.8 GB, IQ3_M is 3.9 GB, Q3_K_M is 4.1 GB, IQ4_XS is 4.6 GB and 1 more.

What context length does Boogu Text Encoder Heretic DHQ support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Boogu Text Encoder Heretic DHQ GGUF?

The files are on Hugging Face in the pottokao/Boogu-Text-Encoder-Heretic-DHQ-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 Boogu Text Encoder Heretic DHQ 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 Q4_K_M quantization requires approximately 6.7 GB at 8 k context, which fits within 8 GB VRAM.

Does this model support vision inference?

The model includes a vision tower but it is intended for use within diffusion pipelines; it does not perform standalone vision inference.

What license applies to this model?

The model is distributed under the Apache‑2.0 license, as stated in the repository.

Other GGUFs of Qwen-Image-2.1-Text-Encoder-Heretic

Similar models

Browse all →

More from pottokao

All by pottokao →

More Qwen models

All Qwen →

Other small models

All small models →