Model Card on HF 🤗: https://huggingface.co/shuttleai/shuttle-3-mini
Shuttle 3 Mini 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)
Shuttle 3 Mini Parameters and Internals
| LLM Name | Shuttle 3 Mini |
| Repository 🤗 | https://huggingface.co/shuttleai/shuttle-3-mini |
| Model Size | 14b |
| Required VRAM | 29.7 GB |
| Updated | 2025-02-05 |
| Maintainer | shuttleai |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.45.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Shuttle 3 Mini
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 14B Instruct 1M | 986K / 29.6 GB | 10662 | 218 |
| Qwen2.5 14B DeepSeek R1 1M | 986K / 29.7 GB | 541 | 7 |
| Impish QWEN 14B 1M | 986K / 29.7 GB | 92 | 10 |
| Calcium Opus 14B Elite 1M | 986K / 29.7 GB | 46 | 10 |
| Q2.5 14B Instruct 1M Harmony | 986K / 29.7 GB | 19 | 1 |
| ...wen2.5 14B Instruct 1M Unalign | 986K / 29.7 GB | 289 | 0 |
| Mergekit Model Stock Injkqri | 986K / 29.7 GB | 18 | 1 |
| Lamarck 14B V0.6 | 128K / 29.7 GB | 1210 | 13 |
| Qwen2.5 14B Vimarckoso V3 | 128K / 29.7 GB | 2247 | 11 |
| Calcium Opus 14B Elite | 128K / 29.7 GB | 116 | 10 |
Note: green Score (e.g. "73.2") means that the model is better than shuttleai/shuttle-3-mini .
Rank the Shuttle 3 Mini 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227