Arxiv:2407.10671 4bit Agentic Ar Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Bn Ceb Conversational Cs De Deepseek-r1 En Endpoints compatible Es Fa Finetuned Fr He Hi Id Instruct It Ja Km Ko Lo Ms My Nl Open-llm Pl Pt Quantized Qwen2 Qwen2.5 Reasoning Region:us Ru Safetensors Sharded Synthetic-data Tensorflow Th Tl Tr Trl Unsloth Ur Vi Zh
Model Card on HF 🤗: https://huggingface.co/open-neo/Kyro-n1-3B
Kyro N1 3B Benchmarks
MMLU Pro: 26.92
GPQA: 4.25
MUSR: 9.5
BBH: 25.79
IFEval: 45.95 vs 88 (so35)-47.8%
MATH Lvl 5: 28.55
LLME Score: 0.27638
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)
Kyro N1 3B Parameters and Internals
| LLM Name | Kyro N1 3B |
| Repository 🤗 | https://huggingface.co/open-neo/Kyro-n1-3B |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-05-26 |
| Maintainer | open-neo |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en zh fr es pt de it ru ja ko vi th ar fa he tr cs pl hi bn ur id ms lo my km tl nl |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Kyro N1 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TethysAI Base Reasoning | 32K / 6.2 GB | 55 | 0 |
| ...5 3B Instruct Unsloth Bnb 4bit | 32K / 2.4 GB | 47195 | 7 |
| Athena 1 3B | 32K / 6.2 GB | 3 | 1 |
| Qwen2.5 3B Reasoner | 32K / 6.2 GB | 6 | 0 |
| ...2.5 Coder 3B Instruct Bnb 4bit | 32K / 2 GB | 76079 | 4 |
| QwQ LCoT 3B Instruct | 32K / 6.2 GB | 9 | 5 |
| Test StealthThinker | 32K / 6.2 GB | 6 | 0 |
| Qwen2.5 3B Instruct Chat Sft | 32K / 6.2 GB | 5 | 0 |
| Model 16bit | 32K / 6.2 GB | 7 | 0 |
| ...grid Sft With Reasoning 3epoch | 32K / 6.2 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than open-neo/Kyro-n1-3B .
Rank the Kyro N1 3B 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124