Tiiuae Falcon 40b needs about 17.3 GB of memory at Q2_K (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.8 GB (Q2_K) to 20.1 GB (Q3_K_M).
Tiiuae Falcon 40b is a 41.8B-parameter Falcon model in GGUF format, quantized by tensorblock. Its trained context length is 2K tokens. The repository has 2 quant files, from 15.8 GB (Q2_K) to 20.1 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 15.8 GB | 16.5 GB | Too big | Get file → | |
| Q3_K_M | 20.1 GB | 20.8 GB | Too big | Get file → |
What GPU do you need for Tiiuae Falcon 40b?
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: the best quant that fits is Q3_K_M (20.1 GB file, about 21.6 GB in use).
Which Tiiuae Falcon 40b quant should you choose?
Q2_K (15.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Tiiuae Falcon 40b
How much VRAM does Tiiuae Falcon 40b need?
About 17.3 GB at Q2_K with an 8K context window. That is the 15.8 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 Tiiuae Falcon 40b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tiiuae Falcon 40b GGUF?
It depends on the quant: Q2_K is 15.8 GB, Q3_K_M is 20.1 GB.
What context length does Tiiuae Falcon 40b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.0 GB at 8K and 0.3 GB at 2K.
Where can I download Tiiuae Falcon 40b GGUF?
The files are on Hugging Face in the tensorblock/falcon-40b-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 Tiiuae Falcon 40b 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.