Flex.2 preview needs about 6.3 GB of memory at Q4_1 (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 31 quants, from 1.7 GB (IQ1_S) to 16.3 GB (BF16).
8B parameter text‑to‑image diffusion model with built‑in inpainting and universal control
Flex.2 preview is an 8.16 billion‑parameter diffusion model built on the flux architecture. It supports text‑to‑image generation, inpainting, and universal control inputs such as pose, line, and depth. The model is released under Apache 2.0 and is available in multiple GGUF quantizations.
Good at
- Text‑to‑image generation
- Inpainting
- Universal control inputs
Limits
- 512 token input length
- No vision support beyond text
- Requires 8 k context for memory estimates
Best for
- Creative image generation
- Rapid prototyping of diffusion tools
- Community‑driven model experimentation
Who it’s for. Developers and artists looking for an open‑source text‑to‑image diffusion model with built‑in inpainting and control features. The model is suitable for those who prefer a permissively licensed model and want to experiment with different quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q2_K | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.6 GB | 5.6 GB | Fits | Get file → | |
| IQ4_NL | 4.6 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_S | 4.6 GB | 5.6 GB | Fits | Get file → | |
| IQ4_NL | 4.6 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.6 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q5_0 | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 6.8 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q5_1 | 6.1 GB | 7.4 GB | Tight | Get file → | |
| Q5_1 | 6.2 GB | 7.4 GB | Tight | Get file → | |
| Q5_1 | 6.2 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q8_0 | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q8_0 | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.2 GB | Too big | Get file → | |
| BF16 | 16.3 GB | 18.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (1.72 GB) or Q2_K (2.82 GB). For 16 GB VRAM, Q4_0 (4.6 GB) or Q5_0 (5.7 GB) are good choices. For 24 GB VRAM, Q6_K (6.7 GB) or Q8_0 (8.39 GB) provide higher fidelity. Memory estimates are approximate.
What GPU do you need for Flex.2 preview?
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: the best quant that fits is Q2_K (2.8 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (4.7 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.3 GB file, about 18.8 GB in use).
Which Flex.2 preview quant should you choose?
Q4_1 (5.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ1_S at 1.7 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 Flex.2 preview
How much VRAM does Flex.2 preview need?
About 6.3 GB at Q4_1 with an 8K context window. That is the 5.2 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 Flex.2 preview on an 8 GB GPU?
Yes, with Q6_K: 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 Flex.2 preview GGUF?
It depends on the quant: IQ1_S is 1.7 GB, Q2_K is 2.8 GB, Q3_K_S is 3.5 GB, Q3_K_S is 3.5 GB, Q3_K_S is 3.5 GB, IQ4_XS is 4.4 GB and 25 more.
Where can I download Flex.2 preview GGUF?
The files are on Hugging Face in the Eviation/Flex.2-preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Flex.2 preview 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 Flex.2 preview on 8 GB VRAM?
Yes, using the IQ1_S or Q2_K quantizations which require 2.4 or 3.7 GB of VRAM at 8 k context.
Does Flex.2 preview support image‑to‑image or inpainting?
Yes, inpainting is built into the base model and can be used directly.