Falcon 7b needs about 4.4 GB of memory at BF16 (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU.
Falcon 7b is a 7.22B-parameter Falcon model in GGUF format, quantized by tensorblock. Its trained context length is 2K tokens. The repository has 1 quant file, from 3.9 GB (BF16) to 3.9 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 3.9 GB | 4.4 GB | Fits | Get file → |
What GPU do you need for Falcon 7b?
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: the best quant that fits is BF16 (3.9 GB file, about 4.4 GB in use).
Which Falcon 7b quant should you choose?
BF16 (3.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Falcon 7b
How much VRAM does Falcon 7b need?
About 4.4 GB at BF16 with an 8K context window. That is the 3.9 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 7b on an 8 GB GPU?
Yes, with BF16: the 3.9 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon 7b GGUF?
It depends on the quant: BF16 is 3.9 GB.
What context length does Falcon 7b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.
Where can I download Falcon 7b GGUF?
The files are on Hugging Face in the tensorblock/falcon-7b-sharded-bf16-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.