HI

HiDream I1 Fast

HidreamGGUF by city96Updated 2025-04-17
Download on Hugging Face
Parameters17.1B
Context—
Layers—
Architecturehidream
Smallest quant6.6 GB
Quick answer

HiDream I1 Fast needs about 13.4 GB of memory at Q4_K_M (a 11.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.6 GB (Q2_K) to 34.2 GB (BF16).

HiDream I1 Fast – 17B parameter image generation model

HiDream I1 Fast is a 17.1B parameter image generative foundation model. It delivers high‑quality images across photorealistic, cartoon, and artistic styles. The model is open‑source under the MIT license.

Good at

  • Fast image generation
  • High image quality across styles
  • Instruction‑based editing

Limits

  • No vision support in GGUF format
  • Requires CUDA 12.4 for Flash Attention
  • Large memory for higher quantizations

Best for

  • Rapid prototyping of image generation
  • Creative content creation
  • Research on diffusion models

Who it’s for. Developers and researchers needing a fast, open‑source image generation model. The model is suitable for personal projects, scientific research, and commercial applications under the MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.6 GB 7.9 GB
Tight Get file →
Q3_K_S8.2 GB 9.7 GB
Too big Get file →
Q3_K_M8.8 GB 10.3 GB
Too big Get file →
Q4_010.7 GB 12.4 GB
Too big Get file →
Q4_K_S10.9 GB 12.7 GB
Too big Get file →
Q4_111.5 GB 13.3 GB
Too big Get file →
Q4_K_M11.5 GB 13.4 GB
Too big Get file →
Q5_K_S12.5 GB 14.5 GB
Too big Get file →
Q5_012.7 GB 14.8 GB
Too big Get file →
Q5_K_M13.0 GB 15.1 GB
Too big Get file →
Q5_113.5 GB 15.6 GB
Too big Get file →
Q6_K14.7 GB 16.9 GB
Too big Get file →
Q8_018.7 GB 21.4 GB
Too big Get file →
BF1634.2 GB 38.8 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (6.57 GB) or Q3_K_S (8.22 GB). For 12 GB VRAM, Q4_0 (10.66 GB) or Q4_K_S (10.9 GB) are suitable. Higher quants require more memory; estimates are approximate.

What GPU do you need for HiDream I1 Fast?

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: the best quant that fits is Q2_K (6.6 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (8.8 GB file, about 10.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_1 (13.5 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.7 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (18.7 GB file, about 21.4 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (34.2 GB file, about 38.8 GB in use).

Which HiDream I1 Fast quant should you choose?

Q4_K_M is the usual starting point for HiDream I1 Fast: it balances file size and quality well. Here it is a 11.5 GB file.

The Q8_0 file is 18.7 GB, about 1.6 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 6.6 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

Architecturehidream
Parameters17.1B

Source

Quantized bycity96
FamilyHidream
Licensemit
Downloads (HF)1,359
Last updated2025-04-17

Frequently asked questions about HiDream I1 Fast

How much VRAM does HiDream I1 Fast need?

About 13.4 GB at Q4_K_M with an 8K context window. That is the 11.5 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 HiDream I1 Fast on an 8 GB GPU?

Yes, with Q2_K: the 6.6 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 HiDream I1 Fast GGUF?

It depends on the quant: Q2_K is 6.6 GB, Q3_K_S is 8.2 GB, Q3_K_M is 8.8 GB, Q4_0 is 10.7 GB, Q4_K_S is 10.9 GB, Q4_1 is 11.5 GB and 8 more.

Where can I download HiDream I1 Fast GGUF?

The files are on Hugging Face in the city96/HiDream-I1-Fast-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 HiDream I1 Fast 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 HiDream I1 Fast on 8 GB VRAM?

Yes, the Q2_K quantization is 6.57 GB, which fits 8 GB VRAM with some headroom.

Does the model support text‑to‑image prompts?

Yes, it is instruction‑based and can generate images from text prompts.

Is the model licensed for commercial use?

Yes, the model is MIT licensed, allowing free use for commercial projects.

Similar models

Browse all →

More from city96

All by city96 →

More Hidream models

All Hidream →

Other medium models

All medium models →