Model Card on HF 🤗: https://huggingface.co/TinyPixel/elm
Elm 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)
Elm Parameters and Internals
| LLM Name | Elm |
| Repository 🤗 | https://huggingface.co/TinyPixel/elm |
| Model Size | 3b |
| Required VRAM | 6.8 GB |
| Updated | 2025-07-11 |
| Maintainer | TinyPixel |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.34.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Elm
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 1350 | 4 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1479568 | 1584 |
| Llama 3.2 3B | 128K / 6.5 GB | 233270 | 601 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 25340 | 163 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 2764 | 15 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 31826 | 5 |
| Cogito V1 Preview Llama 3B | 128K / 7.2 GB | 1686 | 95 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 3209 | 1 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 8 | 2 |
| Llama 3.2 3B Bespoke Thought | 128K / 6.4 GB | 970 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than TinyPixel/elm .
Rank the Elm 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? 49533 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124