FL

FLUX.2 klein base 9B

FluxGGUF by leejetUpdated 2026-01-18
Download on Hugging Face
Parameters9.08B
Context—
Layers—
Architecture—
Smallest quant5.6 GB
Quick answer

FLUX.2 klein base 9B needs about 6.8 GB of memory at Q4_0 (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_0) to 10.0 GB (Q8_0).

FLUX.2 klein base 9B – a 9 billion‑parameter image generation model

FLUX.2 klein base 9B is a 9 billion‑parameter rectified flow transformer that generates images from text and supports multi‑reference editing. It is undistilled, offering full training signal for fine‑tuning and research. The model runs on consumer hardware with real‑time inference.

Good at

  • Real‑time image generation
  • Fine‑tuning and LoRA training
  • Creative image editing

Limits

  • No factual knowledge or text accuracy
  • Not suitable for vision tasks
  • License follows original model

Best for

  • Rapid prototyping of image pipelines
  • Custom image generation workflows
  • Research on flow‑based models

Who it’s for. Developers and artists who need a flexible, high‑quality image model that can be fine‑tuned or used in custom pipelines. The model is ideal for those who prioritize control over speed and require a foundation model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_05.6 GB 6.8 GB
Fits Get file →
Q8_010.0 GB 11.7 GB
Too big Get file →

For 8 GB VRAM, use the Q4_0 quant (5.62 GB file, ~6.8 GB memory at 8k context). For 12 GB VRAM, the Q8_0 quant (9.98 GB file, ~11.7 GB memory) is suitable. Memory estimates are approximate.

What GPU do you need for FLUX.2 klein base 9B?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_0 (5.6 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 11.7 GB in use).

Which FLUX.2 klein base 9B quant should you choose?

Q4_0 (5.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters9.08B

Source

Quantized byleejet
FamilyFlux
Downloads (HF)5,112
Last updated2026-01-18

Frequently asked questions about FLUX.2 klein base 9B

How much VRAM does FLUX.2 klein base 9B need?

About 6.8 GB at Q4_0 with an 8K context window. That is the 5.6 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.2 klein base 9B on an 8 GB GPU?

Yes, with Q4_0: the 5.6 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FLUX.2 klein base 9B GGUF?

It depends on the quant: Q4_0 is 5.6 GB, Q8_0 is 10.0 GB.

Where can I download FLUX.2 klein base 9B GGUF?

The files are on Hugging Face in the leejet/FLUX.2-klein-base-9B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run FLUX.2 klein base 9B on 8 GB VRAM?

Yes, using the Q4_0 quant file which requires about 6.8 GB of VRAM at 8k context.

Does the model support text generation?

No, the model is not intended for factual text generation and may produce inaccurate text.

Is the model open‑source for fine‑tuning?

Yes, the weights are open and can be fine‑tuned or used with LoRA training.

Other GGUFs of FLUX.2-klein-base-9B

Similar models

Browse all →

More from leejet

All by leejet →

More Flux models

All Flux →

Other small models

All small models →