Model Card on HF 🤗: https://huggingface.co/rejoicehub/falcon-7b-quant
Falcon 7B Quant Benchmarks
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 7B Quant Parameters and Internals
| LLM Name | Falcon 7B Quant |
| Repository 🤗 | https://huggingface.co/rejoicehub/falcon-7b-quant |
| Model Size | 7b |
| Required VRAM | 4 GB |
| Updated | 2025-06-09 |
| Maintainer | rejoicehub |
| Model Type | falcon |
| Model Files | |
| Model Architecture | FalconForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.31.0 |
| Is Biased | 0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 65024 |
| Torch Data Type | bfloat16 |
Best Alternatives to Falcon 7B Quant
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| F1H10M 0000 | 2K / 13.9 GB | 2529 | 0 |
| Really Tiny Falcon Testing | 2K / 0 GB | 212561 | 0 |
| Saqr 7B Merged | 2K / 13.9 GB | 28 | 1 |
| ... Openassistant Toxicity Reduce | 2K / 30.4 GB | 19 | 0 |
| F1H10M 0000 | 2K / 13.9 GB | 16 | 0 |
| Falcon Chatbot | 2K / 5.5 GB | 13 | 1 |
| Tiny Testing Falcon Alibi | 2K / 0 GB | 8567 | 1 |
| DociproLLM 7B | 2K / 27.8 GB | 21 | 0 |
| New Falcon | 2K / 4.3 GB | 26 | 1 |
| Claire 7B 0.1 Instruct | 2K / 7.2 GB | 36 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than rejoicehub/falcon-7b-quant .
Rank the Falcon 7B Quant 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124