Falcon 180B needs about 43.7 GB of memory at IQ1_M (a 41.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 38.3 GB (IQ1_S) to 47.8 GB (IQ2_XXS).
Falcon 180B is a 180B-parameter Falcon model in GGUF format, quantized by mradermacher. Its trained context length is 2K tokens. The repository has 3 quant files, from 38.3 GB (IQ1_S) to 47.8 GB (IQ2_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 38.3 GB | 39.2 GB | Too big | Get file → | |
| IQ1_M | 41.9 GB | 42.7 GB | Too big | Get file → | |
| IQ2_XXS | 47.8 GB | 48.6 GB | Too big | Get file → |
What GPU do you need for Falcon 180B?
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: 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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ1_M (41.9 GB file, about 43.7 GB in use).
Which Falcon 180B quant should you choose?
IQ1_M (41.9 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 38.3 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
Source
Frequently asked questions about Falcon 180B
How much VRAM does Falcon 180B need?
About 43.7 GB at IQ1_M with an 8K context window. That is the 41.9 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 Falcon 180B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 40.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Falcon 180B GGUF?
It depends on the quant: IQ1_S is 38.3 GB, IQ1_M is 41.9 GB, IQ2_XXS is 47.8 GB.
What context length does Falcon 180B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.3 GB at 8K and 0.3 GB at 2K.
Where can I download Falcon 180B GGUF?
The files are on Hugging Face in the mradermacher/falcon-180B-i1-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 Falcon 180B use?
Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.