TII · falcon
Can I run falcon?
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
7B parameters2K contexttextFALCON 180B TII LICENSE VERSION 1.014 builds
falcon system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| falcon:7b-text-q4_0 | Q4_0 | 3.9 GB | ~6.0 GB(est.) |
| falcon:7b | Q4_0 | 3.9 GB | ~6.0 GB(est.) |
| falcon:7b-text-q8_0 | Q8_0 | 7.1 GB | ~10.6 GB(est.) |
| falcon:7b-instruct-q8_0 | Q8_0 | 7.1 GB | ~10.6 GB(est.) |
| falcon:7b-text-fp16 | F16 | 13.4 GB | ~19.6 GB(est.) |
| falcon:7b-instruct-fp16 | F16 | 13.4 GB | ~19.6 GB(est.) |
| falcon:40b-text-q4_0 | Q4_0 | 22.2 GB | ~32.1 GB(est.) |
| falcon:40b | Q4_0 | 22.2 GB | ~32.1 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run falcon locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run falcon:7b-text-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about falcon
- How much VRAM do I need to run falcon?
- At 4K context, the smallest published build of falcon (Q4_0) needs roughly 6.0 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run falcon without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 6.0 GB of free RAM for the smallest build.
- How big is the falcon download?
- The smallest published build is 3.9 GB. There are 14 builds in total, the largest being 94.5 GB. Leave some extra free disk space beyond the download itself.
- How do I run falcon locally?
- Install Ollama, then run "ollama run falcon:7b-text-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will falcon run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026