LL

Llama 3.2 3B ImageGen

LlamaGGUF by mradermacherUpdated 2025-10-05
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.4 GB
Quick answer

Llama 3.2 3B ImageGen needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.4 GB (Q2_K) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B ImageGen – prompt generator for text‑to‑image models

Llama 3.2 3B ImageGen is a LoRA‑finetuned decoder‑only model specialized for generating cinematic, structured prompts for image synthesis. It is trained on prompt‑gen‑10k‑flux‑sdxl and outputs concise, creative prompt tags. The model is licensed under MIT.

Good at

  • Generating cinematic prompts
  • Creating structured prompt tags
  • Supporting Stable Diffusion XL and Flux

Limits

  • No general chat capability
  • Not suitable for safety‑critical tasks
  • Requires 8k context for estimates

Best for

  • Prompt generation for T2I pipelines
  • Fine‑tuning base for style‑specific LoRA
  • Embedding in image synthesis workflows

Who it’s for. Developers and artists who need high‑quality prompt generation for text‑to‑image models. The model is ideal for those building or extending T2I pipelines and for users who prefer a dedicated prompt generator over a general chat model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 2.8 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q3_K_L1.8 GB 3.3 GB
Fits Get file →
IQ4_XS1.8 GB 3.3 GB
Fits Get file →
Q4_K_S1.9 GB 3.4 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q5_K_S2.3 GB 3.7 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.02 GB, estimated memory 3.5 GB). For 6 GB VRAM, use Q3_K_M (1.69 GB, 3.1 GB). For 4 GB VRAM, use Q2_K (1.36 GB, 2.8 GB). Estimates are approximate.

What GPU do you need for Llama 3.2 3B ImageGen?

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 F16 (6.4 GB file, about 7.9 GB in use).

Which Llama 3.2 3B ImageGen quant should you choose?

Q4_K_M is the usual starting point for Llama 3.2 3B ImageGen: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.4 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 1.4 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

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensemit
Downloads (HF)739
Last updated2025-10-05

Frequently asked questions about Llama 3.2 3B ImageGen

How much VRAM does Llama 3.2 3B ImageGen need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Llama 3.2 3B ImageGen on an 8 GB GPU?

Yes, with F16: 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 Llama 3.2 3B ImageGen GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.7 GB, Q3_K_L is 1.8 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.9 GB and 6 more.

What context length does Llama 3.2 3B ImageGen 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 Llama 3.2 3B ImageGen GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.2-3B-ImageGen-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 Llama 3.2 3B ImageGen use?

Hugging Face lists the license as mit. 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 Llama 3.2 3B ImageGen on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 3.5 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does this model support vision input?

No, it is a text‑only prompt generator and does not process images.

What license applies to this model?

The model is released under the MIT license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other tiny models

All tiny models →