Chroma needs about 11.4 GB of memory at Q8_0 (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Chroma is a 8.9B-parameter Chroma model in GGUF format, quantized by KazumaSensei. The repository has 1 quant file, from 9.7 GB (Q8_0) to 9.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 9.7 GB | 11.4 GB | Too big | Get file → |
What GPU do you need for Chroma?
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: the best quant that fits is Q8_0 (9.7 GB file, about 11.4 GB in use).
Which Chroma quant should you choose?
Q8_0 (9.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Chroma
How much VRAM does Chroma need?
About 11.4 GB at Q8_0 with an 8K context window. That is the 9.7 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 Chroma on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Chroma GGUF?
It depends on the quant: Q8_0 is 9.7 GB.
Where can I download Chroma GGUF?
The files are on Hugging Face in the KazumaSensei/Chroma repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.