Model reference · open weights
Falcon3-1.5-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 TL;DR Model Details This is a 'hacked' version of tiiuae/Falcon3-10B-Base-1.58bit where model weight scales have been injected into ternary model weights in order to make the model compatible with fine-tuning Model Description - Developed by: https://www.tii.ae - Model type: Causal decoder-only - Architecture: Pure-transformer - 1.58bit version - Language(s) (NLP): Mainly English - License: TII Falcon License 2.0 Training details The model has been trained following the training strategies from the recent 1-bit LLM HF blogpost and 1-bit LLM paper. For more details about the training protocol of this model, please refer to the Falcon-3 technical report, section Compression. Usage Currently to use this model you can either rely on Hugging Face transformers library or BitNet library. You can also play with the model using the falcon-1.58bit playground (only for the 7B instruct version). 🤗 transformers BitNet Evaluation We report in the following table our internal pipeline benchmarks: Note evaluation results are normalized score from v2 leaderboard tasks - reported results of original models in the blogpost are raw scores Citation Coming soon ..
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tiiuae |
|---|---|
| Type | Language models |
| Parameters (lead) | 10.3B |
| Context | 32k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | tiiuae/Falcon3-10B-Base |
| Released | 2026-04-30 |
| Popularity | 322 downloads / month |
| Likes | 2 |
| 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 |
|---|---|---|---|---|---|
| Falcon3-10B-Base-1.58bit-prequantized | 10.3B | BF16 | ~23.7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys falcon3-1-5-prequantized for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (falcon3-1-5-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":"falcon3-1-5-prequantized","messages":[{"role":"user","content":"Hello"}]}'
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 ↗
Sources