Flux Fusion DS merge gguf nf4 fp4 fp8 fp16 needs about 8.2 GB of memory at Q4_K_M (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.0 GB (Q2_K) to 23.8 GB (F16).
Flux Fusion DS merge GGUF model with 11.9B parameters
Flux Fusion DS merge is a 11.9B parameter model in the Flux family. It is available in multiple GGUF quantizations ranging from Q2_K to F16. The model supports text-to-image generation with a recommended 4-8 steps.
Good at
- Text-to-image generation
- Smooth ramp from Schnell to Dev variants
- All-in-one versions include VAE, CLIP, T5XXL
Limits
- No vision support in GGUF alone
- Requires custom nodes for ComfyUI
- Large memory for higher quantizations
Best for
- Low‑VRAM inference with Q2_K or Q3_K_S
- Mid‑range GPUs using Q4_0 or Q4_K_M
- High‑end GPUs for F16 precision
Who it’s for. Users needing a Flux model that blends Schnell and Dev characteristics. Suitable for developers who can supply the required text encoders, VAE, and custom nodes for GGUF or BNB usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 5.4 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_S | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_M | 6.9 GB | 8.2 GB | Too big | Get file → | |
| Q4_1 | 7.5 GB | 8.9 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 9.9 GB | Too big | Get file → | |
| Q5_1 | 9.0 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 11.5 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → | |
| F16 | 23.8 GB | 27.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 4.01 GB, memory 5 GB) or Q3_K_S (5.21 GB, 6.3 GB). For 12 GB VRAM, Q4_0 or Q4_K_M (6.78 GB, 8.1 GB) are suitable. If 16 GB or more is available, Q5_0 or Q6_K (8.26 GB, 9.7 GB or 9.83 GB, 11.5 GB) can be used for better quality.
What GPU do you need for Flux Fusion DS merge gguf nf4 fp4 fp8 fp16?
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 Q2_K (4.0 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (5.4 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (23.8 GB file, about 27.1 GB in use).
Which Flux Fusion DS merge gguf nf4 fp4 fp8 fp16 quant should you choose?
Q4_K_M is the usual starting point for Flux Fusion DS merge gguf nf4 fp4 fp8 fp16: it balances file size and quality well. Here it is a 6.9 GB file.
The Q8_0 file is 12.7 GB, about 1.8 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 4.0 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
Frequently asked questions about Flux Fusion DS merge gguf nf4 fp4 fp8 fp16
How much VRAM does Flux Fusion DS merge gguf nf4 fp4 fp8 fp16 need?
About 8.2 GB at Q4_K_M with an 8K context window. That is the 6.9 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 Fusion DS merge gguf nf4 fp4 fp8 fp16 on an 8 GB GPU?
Yes, with Q3_K_M: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Flux Fusion DS merge gguf nf4 fp4 fp8 fp16 GGUF?
It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 5.2 GB, Q3_K_M is 5.4 GB, Q4_0 is 6.8 GB, Q4_K_S is 6.8 GB, Q4_K_M is 6.9 GB and 8 more.
Where can I download Flux Fusion DS merge gguf nf4 fp4 fp8 fp16 GGUF?
The files are on Hugging Face in the Anibaaal/Flux-Fusion-DS-merge-gguf-nf4-fp4-fp8-fp16 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 Fusion DS merge gguf nf4 fp4 fp8 fp16 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 this model on 8 GB VRAM?
Yes, using Q2_K or Q3_K_S quantizations. They require 5 GB or 6.3 GB of VRAM at 8k context.
Do I need additional nodes for ComfyUI?
Yes, a custom node such as city96/ComfyUI-GGUF is required for GGUF versions.
Is there a vision component included?
No, the GGUF versions do not include vision; VAE and CLIP must be supplied separately.