falcon-11B
A model by TII you run on your own computer, offline: how it did in our Arabic test, the size of each of its files as Hugging Face lists it, the memory a conversation takes worked out from the file itself as llama.cpp reserves it, and whether it fits your card and RAM.
The graphics card in your computer
Press the button and your browser reads the name of your computer's graphics card, which we pick in the check if the Lab has it.
The card's name is never sent to our site: it stays in this browser alone until you press "Forget my device".
Can your PC run it?
In GB, as Windows shows it under Settings > System > About.
Everything in the conversation, your questions and the model's answers. A token is a piece of a word.
Going by this page's figures
Pick the graphics card in your computer or type its RAM, and we'll say which of this model's files fit.
We haven't worked out this model's conversation memory: its layer layout isn't checked against llama.cpp yet, so these sums count the file and working memory only, and it needs more.
Specifications
| The model | |
|---|---|
| Parameters | 11.1 billion[1] |
| Longest conversation | 2,048 tokens[2] |
| Licence | unknown[1] |
| GGUF files to download | |
| Q4_K_M file | 6.85 GB[2] |
| Q5_K_M file | 8.2 GB[3] |
| Q6_K file | 9.18 GB[4] |
| Q8_0 file | 11.8 GB[5] |
| The Arabic test | |
| Arabic score | 13 %[6] Run by CoreITen from its Q4_K_M file, with llama.cpp |
| Understanding Arabic text | 20 %[6] |
| Following Arabic instructions | 0 %[6] |
| Does not invent | 19 %[6] |
| Made-up products it gave specs for (of 8) | 7[6] |
| Answers that slipped into another script (of 56) | 0[6] |
Change log
- Page published.
Sources
- [1] tiiuae/falcon-11B on Hugging Face
- [2] mradermacher/falcon-11B-GGUF: falcon-11B.Q4_K_M.gguf
- [3] mradermacher/falcon-11B-GGUF: falcon-11B.Q5_K_M.gguf
- [4] mradermacher/falcon-11B-GGUF: falcon-11B.Q6_K.gguf
- [5] mradermacher/falcon-11B-GGUF: falcon-11B.Q8_0.gguf
- [6] CoreITen's Arabic test of local AI models, version 1