ReluFalcon 40B PowerInfer needs about 29.0 GB of memory at its main file (a 25.5 GB file) with an 8K context window, so it fits on a 32 GB GPU.
ReluFalcon 40B PowerInfer is a 40B-parameter Relufalcon model in GGUF format, quantized by Tiiny. The repository has 1 quant file, from 25.5 GB to 25.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 25.5 GB | 29.0 GB | Too big | Get file → |
What GPU do you need for ReluFalcon 40B PowerInfer?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is the main file (25.5 GB file, about 29.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ReluFalcon 40B PowerInfer
How much VRAM does ReluFalcon 40B PowerInfer need?
About 29.0 GB at its main file with an 8K context window. That is the 25.5 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 ReluFalcon 40B PowerInfer on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ReluFalcon 40B PowerInfer GGUF?
It depends on the quant: file is 25.5 GB.
Where can I download ReluFalcon 40B PowerInfer GGUF?
The files are on Hugging Face in the Tiiny/ReluFalcon-40B-PowerInfer-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 ReluFalcon 40B PowerInfer use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.