llm 3 2 flux prompt needs about 4.1 GB of memory at Q6_K (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.3 GB (Q5_K_S) to 6.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
LLM 3.2 Flux Prompt – fine‑tuned for image prompt generation
LLM 3.2 Flux Prompt is a 3.21 B parameter Llama‑3.2 model fine‑tuned to produce high‑quality image prompts for text‑to‑image models. It is optimized for nuanced and precise prompt creation and integrates with ComfyUI. The model is released under the llama3.2 license.
Good at
- Generating detailed image prompts
- Optimized for Flux and similar text‑to‑image models
- Fine‑tuned prompt style variety
Limits
- No vision support
- Requires 8 k context for estimates
- License restricts commercial use
Best for
- Creative writing assistance
- Digital art prompt creation
- Enhancing text‑to‑image inputs
Who it’s for. Developers and artists who need precise prompts for text‑to‑image generation. Suitable for local deployment via llama.cpp or compatible GUIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| — | 6.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, use Q5_K_S (2.27 GB file, ~3.7 GB memory) or Q5_K_M (2.32 GB file, ~3.8 GB memory). If 12 GB VRAM is available, Q6_K (2.64 GB file, ~4.1 GB memory) is a good balance. Larger models require more memory.
What GPU do you need for llm 3 2 flux prompt?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q5_K_M (2.3 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (6.4 GB file, about 7.9 GB in use).
Which llm 3 2 flux prompt quant should you choose?
Q6_K (2.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_S at 2.3 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llm 3 2 flux prompt
How much VRAM does llm 3 2 flux prompt need?
About 4.1 GB at Q6_K with an 8K context window. That is the 2.6 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 llm 3 2 flux prompt on an 8 GB GPU?
Yes, with the smaller files: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llm 3 2 flux prompt GGUF?
It depends on the quant: Q5_K_S is 2.3 GB, Q5_K_M is 2.3 GB, Q6_K is 2.6 GB, Q8_0 is 3.4 GB, file is 6.4 GB.
What context length does llm 3 2 flux prompt support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download llm 3 2 flux prompt GGUF?
The files are on Hugging Face in the MaziyarPanahi/llm_3_2_flux_prompt-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 llm 3 2 flux prompt use?
Hugging Face lists the license as llama3.2. 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 the Q5_K_S or Q5_K_M quantizations will fit within 8 GB VRAM with an estimated 3.7–3.8 GB memory usage.
Does this model support vision tasks?
No, the model is purely text‑based and does not include vision capabilities.
What license applies to this model?
The model is released under the llama3.2 license, which may restrict commercial use.