Model Card on HF 🤗: https://huggingface.co/prem-research/prem-1B-SQL
Prem 1B SQL 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)
Prem 1B SQL Parameters and Internals
| LLM Name | Prem 1B SQL |
| Repository 🤗 | https://huggingface.co/prem-research/prem-1B-SQL |
| Model Size | 1b |
| Required VRAM | 5.4 GB |
| Updated | 2025-10-04 |
| Maintainer | premai-io |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.44.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 32256 |
| Torch Data Type | float32 |
Best Alternatives to Prem 1B SQL
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 02 Nano Llama 3.2 1B | 1024K / 2.5 GB | 73 | 3 |
| LWM Text Chat 1M | 1024K / 13.5 GB | 1730 | 174 |
| LWM Text 1M | 1024K / 13.5 GB | 237 | 29 |
| JOSIE 1M Base | 1024K / 13.5 GB | 12 | 1 |
| JOSIE 1M Base | 1024K / 13.5 GB | 6 | 1 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 5464491 | 1116 |
| Llama 3.2 1B | 128K / 2.5 GB | 3306012 | 2082 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 231706 | 78 |
| ...enchmaxx Llama 3.2 1B Instruct | 128K / 0 GB | 179 | 3 |
| ...ice In The Dark RP NSFW 3.2 1B | 128K / 3 GB | 125 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than prem-research/prem-1B-SQL .
Rank the Prem 1B SQL 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? 51540 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124