flux2 dev turbo Q4 K M needs about 21.5 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, so it fits on a 24 GB GPU.
32B FLUX.2-dev with Turbo LoRA, Q4_K_M quantized
The flux2 dev turbo Q4 K M model is a 32.2B parameter FLUX.2-dev with Turbo LoRA baked into the UNET weights. It is quantized to Q4_K_M using a custom llama.cpp build for the FLUX architecture. The merged file eliminates low‑VRAM patches and fits in 24 GB VRAM on RTX 3090/4090.
Good at
- Fast generation with Turbo LoRA
- Zero low‑VRAM patches
- Full 32B model in GGUF format
Limits
- Requires ~21.5 GB VRAM at 8k context
- No dynamic LoRA loading
- No explicit license info
Best for
- Stable diffusion image generation
- Fast inference on RTX 3090/4090
- Low‑VRAM optimized workflows
Who it’s for. Users with RTX 3090 or 4090 GPUs who need the full 32B FLUX.2-dev model with Turbo LoRA baked in. Ideal for ComfyUI users wanting maximum speed without applying LoRA nodes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 18.7 GB | 21.5 GB | Too big | Get file → |
For 24 GB VRAM, the Q4_K_M quantized file (~18.71 GB) is suitable. If you have 32 GB+ RAM, the model will load comfortably. Avoid larger quantizations as they are not provided.
What GPU do you need for flux2 dev turbo Q4 K M?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (18.7 GB file, about 21.5 GB in use).
Which flux2 dev turbo Q4 K M quant should you choose?
Q4_K_M is the usual starting point for flux2 dev turbo Q4 K M: it balances file size and quality well. Here it is a 18.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flux2 dev turbo Q4 K M
How much VRAM does flux2 dev turbo Q4 K M need?
About 21.5 GB at Q4_K_M with an 8K context window. That is the 18.7 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 flux2 dev turbo Q4 K M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of flux2 dev turbo Q4 K M GGUF?
It depends on the quant: Q4_K_M is 18.7 GB.
Where can I download flux2 dev turbo Q4 K M GGUF?
The files are on Hugging Face in the UDream/flux2-dev-turbo-Q4_K_M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
No, the model requires about 21.5 GB VRAM at 8k context and is designed for 24 GB VRAM GPUs.
Do I need to load a LoRA node?
No, the Turbo LoRA is already baked into the UNET weights; do not use a Load LoRA node.
What hardware is recommended?
RTX 3090 or 4090 with at least 24 GB VRAM and 32 GB+ RAM for optimal performance.