Falcon 1B Stage3 2 is an open-source language model by euclaise. Features: 1b LLM, VRAM: 2.6GB, Context: 2K, License: apache-2.0, HF Score: 36.2, LLM Explorer Score: 0.14, Arc: 34.6, HellaSwag: 58.4, MMLU: 23.9, TruthfulQA: 39.9, WinoGrande: 60.5.
Base model:euclaise/falcon 1b ... Base model:finetune:euclaise/f... Custom code Endpoints compatible Falcon Generated from trainer Pytorch Region:us
Model Card on HF 🤗: https://huggingface.co/euclaise/falcon_1b_stage3_2
Falcon 1b Stage3 2 Benchmarks
ARC: 34.56 vs 96.7 (so35)-64.3%
HellaSwag: 58.37 vs 95.3 (gpt4)-38.8%
MMLU: 23.87 vs 88.3 (so35)-73%
TruthfulQA: 39.89 vs 59 (gpt4)-32.4%
WinoGrande: 60.46 vs 87.5 (gpt4)-30.9%
LLME Score: 0.13691
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Falcon 1B Stage3 2 Parameters and Internals
| LLM Name | Falcon 1b Stage3 2 |
| Repository 🤗 | https://huggingface.co/euclaise/falcon_1b_stage3_2 |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2.6 GB |
| Updated | 2026-01-21 |
| Maintainer | euclaise |
| Model Type | falcon |
| Model Files | |
| Model Architecture | FalconForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.33.2 |
| Is Biased | 1 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <|endoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <|endoftext|> |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Falcon 1B Stage3 2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Neuralfalcon 1B V1 | 2K / 2.8 GB | 662 | 0 |
| Falcon Rw 1B Instruct Openorca | 2K / 2.6 GB | 1011 | 11 |
| Falcon Rw 1B Chat | 2K / 2.6 GB | 758 | 3 |
| Falcon 1b Stage2 | 2K / 2.6 GB | 3060 | 3 |
| Falcon 1b Stage1 | 2K / 2.6 GB | 1520 | 0 |
| Falcon 1b Stage3 | 2K / 2.6 GB | 9 | 0 |
| INTERS Falcon 1B | 2K / 0.7 GB | 568 | 1 |
| Crow 1B Attempt1 | 2K / 5.3 GB | 38 | 3 |
| HelpingAI Lite Chat | 2K / 2.6 GB | 5 | 4 |
| Alphaca 1B | 2K / 2.6 GB | 341 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than euclaise/falcon_1b_stage3_2 .
Rank the Falcon 1B Stage3 2 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52758 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a