Total runs:
346.3K
Run Growth:
-684.4K
Growth Rate:
-197.24%
Sponsored by
Agentkit
tiiuae / Falcon-E-3B-Instruct
Model's Last Updated: October 07 2025
text-generation
Introduction of Falcon-E-3B-Instruct
Model Details of Falcon-E-3B-Instruct
Table of Contents
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:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "tiiuae/Falcon-E-3B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
).to("cuda")
# Perform text generation
If you want to rather use the classic
bfloat16
version, you can run:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "tiiuae/Falcon-E-3B-Instruct"
revision = "bfloat16"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
revision=revision,
).to("cuda")
# Perform text generation
BitNet
git clone https://github.com/microsoft/BitNet && cd BitNet
pip install -r requirements.txt
python setup_env.py --hf-repo tiiuae/Falcon-E-3B-Instruct -q i2_s
python run_inference.py -m models/Falcon-E-3B-Instruct/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
Fine-tuning
For fine-tuning the model, you should load the
prequantized
revision of the model and use the
onebitllms
Python package:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import SFTTrainer
+ from onebitllms import replace_linear_with_bitnet_linear, quantize_to_1bit
model_id = "tiiuae/Falcon-E-3B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id, revision="prequantized")
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
+ revision="prequantized"
)
+ model = replace_linear_with_bitnet_linear(model)
trainer = SFTTrainer(
model,
...
)
trainer.train()
+ quantize_to_1bit(output_directory)
Evaluation
We report in the following table our internal pipeline benchmarks:
Note evaluation results are normalized score from former Hugging Face leaderboard v2 tasks
For 1B scale models and below
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| Qwen-2.5-0.5B | 0.5B | 1GB | 16.27 | 3.93 | 0.0 | 2.08 | 6.95 | 10.06 | 6.55 |
| SmolLM2-360M | 0.36B | 720MB | 21.15 | 1.21 | 0.0 | 7.73 | 5.54 | 1.88 | 6.25 |
| Qwen-2.5-1.5B | 1.5B | 3.1GB | 26.74 | 9.14 | 16.66 | 5.27 | 20.61 | 4.7 | 13.85 |
| Llama-3.2-1B | 1.24B | 2.47GB | 14.78 | 1.21 | 4.37 | 2.56 | 2.26 | 0 | 4.2 |
| SmolLM2-1.7B | 1.7B | 3.4GB | 24.4 | 2.64 | 9.3 | 4.6 | 12.64 | 3.91 | 9.58 |
| Falcon-3-1B-Base | 1.5B | 3GB | 24.28 | 3.32 | 11.34 | 9.71 | 6.76 | 3.91 | 9.89 |
| Hymba-1.5B-Base | 1.5B | 3GB | 22.95 | 1.36 | 7.69 | 5.18 | 10.25 | 0.78 | 8.04 |
| Falcon-E-1B-Base | 1.8B | 635MB | 32.9 | 10.97 | 2.8 | 3.65 | 12.28 | 17.82 | 13.40 |
For 3B scale models
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| Falcon-3-3B-Base | 3B | 6.46GB | 15.74 | 11.78 | 21.58 | 6.27 | 18.09 | 6.26 | 15.74 |
| Qwen2.5-3B | 3B | 6.17GB | 26.9 | 14.8 | 24.3 | 11.76 | 24.48 | 6.38 | 18.1 |
| Falcon-E-3B-Base | 3B | 955MB | 36.67 | 13.45 | 8.67 | 4.14 | 19.83 | 27.16 | 18.32 |
Below are the results for instruction fine-tuned models:
For 1B scale models and below
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| Qwen-2.5-0.5B-Instruct | 500M | 1GB | 30.71 | 0 | 8.43 | 0.94 | 7.75 | 0 | 6.59 |
| SmolLM2-360M-Instruct | 360M | 720MB | 38.42 | 1.51 | 4.17 | 2.77 | 1.3 | 0.67 | 8.14 |
| Qwen-2.5-1.5B-Instruct | 1.5B | 3.1GB | 44.76 | 22.05 | 19.81 | 3.19 | 19.99 | 0.78 | 18.43 |
| SmolLM2-1.7B | 1.7B | 3.4GB | 53.68 | 5.82 | 10.92 | 4.1 | 11.71 | 0 | 15.02 |
| Falcon-3-1B-Instruct | 1.5B | 3GB | 55.57 | 6.34 | 12.96 | 10.56 | 9.32 | 2.24 | 16.16 |
| Hymba-1.5B-Instruct | 1.5B | 3GB | 60.09 | 2.72 | 4.59 | 1.05 | 11.56 | 5.515 | 14.19 |
| Falcon-E-1B-Instruct | 1.8B | 635MB | 54.35 | 9.12 | 16.5 | 2.51 | 19.42 | 9.64 | 18.59 |
For 3B scale models
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|---|---|---|---|---|---|---|---|---|---|
| Falcon-3-3B-Instruct | 3B | 6.46GB | 69.77 | 25 | 26.29 | 11.13 | 22.28 | 5.15 | 26.6 |
| Qwen2.5-3B-Instruct | 3B | 6.17GB | 64.75 | 36.78 | 25.8 | 7.57 | 25.05 | 3.02 | 27.16 |
| Falcon-E-3B-Instruct | 3B | 955MB | 60.97 | 15.3 | 23.59 | 2.12 | 26.45 | 7.45 | 22.64666667 |
Useful links
- View our release blogpost .
-
Learn more about
onebitllmslibrary . - 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.
@misc{tiionebitllms,
title = {Falcon-E, a series of powerful, universal and fine-tunable 1.58bit language models.},
author = {Falcon-LLM Team},
month = {April},
url = {https://falcon-lm.github.io/blog/falcon-edge},
year = {2025}
}
Runs of tiiuae Falcon-E-3B-Instruct on huggingface.co
1.3K
Total runs
0
24-hour runs
51
3-day runs
62
7-day runs
378
30-day runs
More Information About Falcon-E-3B-Instruct huggingface.co Model
Url of Falcon-E-3B-Instruct
Falcon-E-3B-Instruct huggingface.co Url
Provider of Falcon-E-3B-Instruct huggingface.co
Other API from tiiuae
Updated:October 12 2024
Total runs:
105.9K
Run Growth:
11.1K
Growth Rate:
10.49%
Total runs:
60.1K
Run Growth:
32.3K
Growth Rate:
53.81%
Total runs:
44.6K
Run Growth:
-125.2K
Growth Rate:
-280.36%
Total runs:
31.8K
Run Growth:
-172
Growth Rate:
-0.53%
Total runs:
21.2K
Run Growth:
-2.7K
Growth Rate:
-12.84%
Total runs:
16.6K
Run Growth:
-508
Growth Rate:
-3.06%
Total runs:
15.8K
Run Growth:
-1.9K
Growth Rate:
-12.24%
Total runs:
15.3K
Run Growth:
1.1K
Growth Rate:
6.85%
Total runs:
14.7K
Run Growth:
-9.1K
Growth Rate:
-61.46%
Total runs:
13.3K
Run Growth:
-3.5K
Growth Rate:
-26.36%
Total runs:
11.7K
Run Growth:
-554
Growth Rate:
-4.74%
Total runs:
9.2K
Run Growth:
5.3K
Growth Rate:
57.78%
Total runs:
8.4K
Run Growth:
1.6K
Growth Rate:
18.87%
Total runs:
8.0K
Run Growth:
341
Growth Rate:
4.24%
Total runs:
7.5K
Run Growth:
1.5K
Growth Rate:
20.17%
Total runs:
6.5K
Run Growth:
-819
Growth Rate:
-12.56%
Total runs:
5.0K
Run Growth:
1.9K
Growth Rate:
37.53%
Total runs:
4.6K
Run Growth:
2.1K
Growth Rate:
45.56%
Total runs:
4.0K
Run Growth:
1.4K
Growth Rate:
34.67%
Total runs:
3.9K
Run Growth:
2.4K
Growth Rate:
55.76%
Total runs:
3.7K
Run Growth:
-967
Growth Rate:
-25.92%
Total runs:
3.2K
Run Growth:
31
Growth Rate:
0.96%
Total runs:
3.1K
Run Growth:
1.7K
Growth Rate:
56.84%
Total runs:
2.6K
Run Growth:
1.7K
Growth Rate:
66.82%
Total runs:
2.3K
Run Growth:
1.8K
Growth Rate:
80.17%
Total runs:
1.7K
Run Growth:
132
Growth Rate:
7.99%
Total runs:
1.6K
Run Growth:
636
Growth Rate:
40.80%
Total runs:
1.5K
Run Growth:
-145
Growth Rate:
-9.97%
Total runs:
1.3K
Run Growth:
851
Growth Rate:
65.61%
Total runs:
1.3K
Run Growth:
18
Growth Rate:
1.40%
Total runs:
1.3K
Run Growth:
952
Growth Rate:
76.16%
Total runs:
988
Run Growth:
0
Growth Rate:
0.00%
Total runs:
986
Run Growth:
36
Growth Rate:
3.65%
Total runs:
914
Run Growth:
-396
Growth Rate:
-43.33%
Total runs:
851
Run Growth:
106
Growth Rate:
12.46%
Total runs:
769
Run Growth:
-363
Growth Rate:
-47.20%
Total runs:
683
Run Growth:
-200
Growth Rate:
-29.28%
Total runs:
532
Run Growth:
18
Growth Rate:
3.38%
Total runs:
525
Run Growth:
522
Growth Rate:
99.43%
Total runs:
500
Run Growth:
-33
Growth Rate:
-6.60%
Total runs:
482
Run Growth:
-23
Growth Rate:
-4.77%
Total runs:
473
Run Growth:
81
Growth Rate:
17.12%
Total runs:
446
Run Growth:
20
Growth Rate:
4.48%
Total runs:
400
Run Growth:
109
Growth Rate:
27.25%
Total runs:
385
Run Growth:
131
Growth Rate:
34.03%
Total runs:
383
Run Growth:
-51
Growth Rate:
-13.32%
Total runs:
327
Run Growth:
20
Growth Rate:
6.12%
Total runs:
324
Run Growth:
-231
Growth Rate:
-71.30%
Total runs:
317
Run Growth:
4
Growth Rate:
1.26%
Total runs:
311
Run Growth:
17
Growth Rate:
5.47%
Total runs:
306
Run Growth:
274
Growth Rate:
89.54%
Total runs:
293
Run Growth:
45
Growth Rate:
15.36%
Total runs:
273
Run Growth:
246
Growth Rate:
90.11%
Total runs:
223
Run Growth:
-212
Growth Rate:
-95.07%
Total runs:
201
Run Growth:
82
Growth Rate:
40.80%
Total runs:
200
Run Growth:
-433
Growth Rate:
-216.50%
Total runs:
193
Run Growth:
-24
Growth Rate:
-12.44%
Total runs:
190
Run Growth:
80
Growth Rate:
42.11%
Total runs:
181
Run Growth:
-80
Growth Rate:
-44.20%
Total runs:
176
Run Growth:
74
Growth Rate:
42.05%
Total runs:
175
Run Growth:
47
Growth Rate:
26.86%
Total runs:
167
Run Growth:
7
Growth Rate:
4.19%
Total runs:
166
Run Growth:
12
Growth Rate:
7.23%
Total runs:
154
Run Growth:
64
Growth Rate:
41.56%
Total runs:
147
Run Growth:
60
Growth Rate:
40.82%
Total runs:
136
Run Growth:
15
Growth Rate:
11.03%
Total runs:
112
Run Growth:
18
Growth Rate:
16.07%
Total runs:
107
Run Growth:
-231
Growth Rate:
-215.89%
Total runs:
105
Run Growth:
19
Growth Rate:
18.10%
Total runs:
97
Run Growth:
97
Growth Rate:
100.00%
Total runs:
77
Run Growth:
24
Growth Rate:
31.17%
Total runs:
72
Run Growth:
72
Growth Rate:
100.00%
Total runs:
62
Run Growth:
7
Growth Rate:
11.29%
Total runs:
60
Run Growth:
-4
Growth Rate:
-6.67%
Total runs:
59
Run Growth:
-149
Growth Rate:
-252.54%
Total runs:
55
Run Growth:
21
Growth Rate:
38.18%
Total runs:
52
Run Growth:
0
Growth Rate:
0.00%
Total runs:
50
Run Growth:
1
Growth Rate:
2.00%
Total runs:
42
Run Growth:
16
Growth Rate:
38.10%
Total runs:
40
Run Growth:
15
Growth Rate:
37.50%
Total runs:
40
Run Growth:
17
Growth Rate:
42.50%
Total runs:
39
Run Growth:
9
Growth Rate:
23.08%
Total runs:
39
Run Growth:
-59
Growth Rate:
-151.28%