Model reference · open weights
Falcon-E-prequantized is an open-weight language model from tiiuae, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Table of Contents 0. TL;DR 1. Model Details 2. Training Details 3. Usage 4. Evaluation 5. Citation This is simply the mirror of https://huggingface.co/tiiuae/Falcon-E-3B-Base - branch prequantized TL;DR Model Details Model Description - Developed by: https://www.tii.ae - Model type: Causal decoder-only / Base version - Architecture: Pure-transformer - 1.58bit version - Language(s) (NLP): English - License: Falcon-LLM License Training details For more details about the training protocol of this model, please refer to the Falcon-E technical blogpost. Usage Currently to use this model you can either rely on Hugging Face transformers library or BitNet library. There are multiple ways to interact with the model depending on your target usage. For each of the Falcon-E series model, you have three variants: the BitNet model, the prequantized checkpoint for fine-tuning and the bfloat16 version of the BitNet model. Inference 🤗 transformers In case you want to perform inference on the BitNet checkpoint run: If you want to rather use the classic bfloat16 version, you can run: BitNet Apply mlx-lm Then: Fine-tuning For fine-tuning the model, you should load the prequantized revision of the model and use the onebitllms Python package: Evaluation We report in the following table our internal pipeline benchmarks: Note evaluation results are normalized score from former Hugging Face leaderboard v2 tasks Below are the results for instruction fine-tuned models: Useful links - View our release blogpost. - Learn more about onebitllms library. - Feel free to join our discord server if you have any questions or to interact with our researchers and developers. Citation If the Falcon-E family of models were helpful to your work, feel free to give us a cite.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tiiuae |
|---|---|
| Type | Language models |
| Parameters (lead) | 3.1B |
| Context | 32k tokens |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-04-22 |
| Popularity | 149 downloads / month |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Falcon-E-3B-Base-prequantized | 3.1B | BF16 | ~7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys falcon-e-prequantized for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (falcon-e-prequantized below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"falcon-e-prequantized","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗