FLUX.2 Klein 9B KV needs about 6.9 GB of memory at Q4_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 9 quants, from 3.6 GB (Q2_K) to 10.0 GB (Q8_0).
FLUX.2 Klein 9B KV – a 9‑billion‑parameter diffusion model in GGUF format
FLUX.2 Klein 9B KV is a 9‑billion‑parameter diffusion model converted to GGUF by QuantStack. It supports image generation and editing via ComfyUI custom nodes. The model is available in several quantization levels, ranging from Q2_K to Q8_0.
Good at
- Image generation
- Image editing
- Low‑latency inference on modest GPUs
Limits
- No vision support in GGUF form
- License terms inherited from original model
- Requires ComfyUI custom node for use
Best for
- Creative image generation projects
- Rapid prototyping of diffusion pipelines
- Educational demos of diffusion models
Who it’s for. Developers and researchers who need a compact diffusion model for local inference. The model is suitable for those using ComfyUI and who can comply with the original licensing terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_S | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_S | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_M | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_M | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q8_0 | 10.0 GB | 11.7 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.72 GB file, ~6.9 GB memory) is a good balance. If 12 GB VRAM is available, Q5_K_M (6.81 GB file, ~8.1 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (7.87 GB file, ~9.3 GB memory) or Q8_0 (9.98 GB file, ~11.7 GB memory) can be used.
What GPU do you need for FLUX.2 Klein 9B KV?
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: the best quant that fits is Q3_K_M (4.6 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (6.7 GB file, about 8.0 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 9B KV quant should you choose?
Q4_K_M is the usual starting point for FLUX.2 Klein 9B KV: it balances file size and quality well. Here it is a 5.7 GB file.
The Q8_0 file is 10.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.6 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
Source
Frequently asked questions about FLUX.2 Klein 9B KV
How much VRAM does FLUX.2 Klein 9B KV need?
About 6.9 GB at Q4_K_M with an 8K context window. That is the 5.7 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.2 Klein 9B KV on an 8 GB GPU?
Yes, with Q5_K_S: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.2 Klein 9B KV GGUF?
It depends on the quant: Q2_K is 3.6 GB, Q3_K_S is 4.5 GB, Q3_K_M is 4.6 GB, Q4_K_S is 5.6 GB, Q4_K_M is 5.7 GB, Q5_K_S is 6.7 GB and 3 more.
Where can I download FLUX.2 Klein 9B KV GGUF?
The files are on Hugging Face in the QuantStack/FLUX.2-Klein-9B-KV-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.2 Klein 9B KV use?
Hugging Face lists the license as other. 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 FLUX.2 Klein 9B KV on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantizations, which require approximately 6.9 GB or 6.8 GB of VRAM at 8k context.
Does the model support image editing?
Yes, the GGUF conversion includes a KV Cache node that enables editing without limiting capabilities.
What license applies to the GGUF file?
The original licensing terms of black-forest-labs/FLUX.2-klein-9b-kv remain in effect for the GGUF file.