FLUX.3 Klein Text Encoder Heretic DHQ needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 0.0 GB to 2.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
FLUX.3 Klein Text Encoder Heretic DHQ – Qwen3-VL-4B-Instruct based
FLUX.3 Klein Text Encoder Heretic DHQ is a Qwen3-VL-4B-Instruct derived text encoder. It uses Dual-Head Quant (DHQ) for efficient precision allocation. The model supports coding, tools, and vision tasks.
Good at
- Vision‑language encoding
- Coding and tool integration
- Multimodal reasoning
Limits
- No vision support in this encoder alone
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Integrating with FLUX.3 Klein DiT
- Using as prompt enhancer in Dual‑Head Dragon
- Loading via ComfyUI or llama.cpp
Who it’s for. Developers building vision‑language pipelines that need a lightweight text encoder. It is suitable for projects that already use FLUX.3 Klein or Qwen3-VL-4B-Instruct models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.4 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quantized file (2.66 GB) which estimates 4.4 GB at 8k context. If more memory is available, the unknown quant file (1.7 GB) can be used for lower memory usage. Estimates are approximate.
What GPU do you need for FLUX.3 Klein 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: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.4 GB in use).
Which FLUX.3 Klein Text Encoder Heretic DHQ quant should you choose?
Q4_K_M is the usual starting point for FLUX.3 Klein Text Encoder Heretic DHQ: it balances file size and quality well. Here it is a 2.7 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
Source
Frequently asked questions about FLUX.3 Klein Text Encoder Heretic DHQ
How much VRAM does FLUX.3 Klein Text Encoder Heretic DHQ need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 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 FLUX.3 Klein Text Encoder Heretic DHQ on an 8 GB GPU?
Yes, with Q4_K_M: the 2.7 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.3 Klein Text Encoder Heretic DHQ GGUF?
It depends on the quant: file is 0.0 GB, Q4_K_M is 2.7 GB.
What context length does FLUX.3 Klein 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 FLUX.3 Klein Text Encoder Heretic DHQ GGUF?
The files are on Hugging Face in the pottokao/FLUX.3-Klein-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 FLUX.3 Klein 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 the Q4_K_M quantized file on 8 GB VRAM?
Yes, the Q4_K_M file is 2.66 GB and estimates 4.4 GB at 8k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
The text encoder itself does not process vision; it is used alongside a vision model such as FLUX.3 Klein DiT.
What license applies to this model?
The model is released under the apache-2.0 license.