Downloads · 30 days
458
5% of all-time downloads
Chroma-GGUF
Clybius/Chroma-GGUF
Chroma-GGUF is a machine learning model from Clybius. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Chroma is a 8.9 billion parameter rectified flow transformer capable of generating images from text descriptions. Based on FLUX.1 [schnell] with heavy architectural modifications.
All-time downloads
8.8K
Public
Repo size
44.8 GB
Likes
32
Public
Repo makeup
Click a slice to open those files.
.gguf44.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 5, 2025
- Updated
- Apr 29, 2025
- SHA
- 9681d7cb
Base models
Model card
From the Hugging Face model README
Chroma is a 8.9 billion parameter rectified flow transformer capable of generating images from text descriptions.
Based on FLUX.1 [schnell] with heavy architectural modifications.
It is recommended to use Scaled FP8 or these updated GGUFs instead!
Quantized into GGUF format using a modified llama.cpp & city96's ComfyUI-GGUF/tools. Distillation layers are not quantized.
Also see silveroxides' Chroma GGUFs! (BF16, Q8_0, Q6_K, Q5_K_S, Q5_1, Q5_0, Q4_K_M, Q4_1, Q4_0, Q3_K_L)
Q*_M GGUFs are mixed quantizations with an aim at maximizing speed by selectively choosing the quantization of certain layers.
- Q8_M focuses on Q8_0 quantization of weights for performance, mixed with Q6_K on less heavy layers.
- License
- apache-2.0
- Created
- Mar 5, 2025
- Updated
- Apr 29, 2025