Model Card on HF 🤗: https://huggingface.co/rubricreward/R3-Qwen3-4B-LoRA-5K-v1.1
R3 Qwen3 4B LoRA 5K V1.1 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)
R3 Qwen3 4B LoRA 5K V1.1 Parameters and Internals
| LLM Name | R3 Qwen3 4B LoRA 5K V1.1 |
| Repository 🤗 | https://huggingface.co/rubricreward/R3-Qwen3-4B-LoRA-5K-v1.1 |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2025-07-20 |
| Maintainer | rubricreward |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to R3 Qwen3 4B LoRA 5K V1.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Jan Nano 128K | 128K / 8.1 GB | 6412 | 200 |
| Polaris 4B Preview | 128K / 8.1 GB | 3262 | 119 |
| Jan Nano 128K | 128K / 8.1 GB | 729 | 2 |
| Jan Nano | 40K / 8.1 GB | 20757 | 462 |
| Qwen3 Embedding 4B | 40K / 8.1 GB | 106356 | 101 |
| Qwen3 Reranker 4B | 40K / 8.1 GB | 57163 | 75 |
| Qwen3 4B | 40K / 8.1 GB | 27193 | 11 |
| P1 V4 | 40K / 8.1 GB | 608 | 0 |
| QVikhr 3 4B Instruction | 40K / 8.1 GB | 811 | 12 |
| P1 V1 | 40K / 8.1 GB | 455 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than rubricreward/R3-Qwen3-4B-LoRA-5K-v1.1 .
Rank the R3 Qwen3 4B LoRA 5K V1.1 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124