Qwen2.5 3B R1 Rearc Stage1 is an open-source language model by spinech. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, Instruction-Based, LLM Explorer Score: 0.17.
Arxiv:2402.03300 Ara Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Conversational Deu Endpoints compatible Eng Fra Generated from trainer Grpo Instruct Ita Jpn Kor Por Qwen2 Region:us Rus Safetensors Sharded Spa Tensorboard Tensorflow Tha Trl Vie Zho
Model Card on HF 🤗: https://huggingface.co/spinech/qwen2.5-3b-r1-rearc-stage1
Qwen2.5 3B R1 Rearc Stage1 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)
Qwen2.5 3B R1 Rearc Stage1 Parameters and Internals
| LLM Name | Qwen2.5 3B R1 Rearc Stage1 |
| Repository 🤗 | https://huggingface.co/spinech/qwen2.5-3b-r1-rearc-stage1 |
| Model Name | qwen-2.5-3b-r1-rearc |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2026-05-19 |
| Maintainer | spinech |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 3B R1 Rearc Stage1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba2 3B | 128K / 6.2 GB | 24 | 0 |
| Tessa T1 3B | 117K / 6.2 GB | 26 | 5 |
| UIGEN T1.5 3B | 117K / 6.2 GB | 10 | 1 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 9441068 | 450 |
| SmallThinker 3B Preview | 32K / 6.8 GB | 30529 | 412 |
| LeeChanRX 3B Instruct | 32K / 6.2 GB | 166 | 0 |
| FlameDesigner Qwen2.5 3B V1 | 32K / 6.2 GB | 233 | 0 |
| BastiAI 2 Instruct | 32K / 6.2 GB | 81 | 0 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 451109 | 101 |
| Phoenix Qwen2.5 3B V1 | 32K / 6.2 GB | 17 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than spinech/qwen2.5-3b-r1-rearc-stage1 .
Rank the Qwen2.5 3B R1 Rearc Stage1 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? 53834 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a