Base model:finetune:powerinfer... Base model:powerinfer/smallthi... Conversational Dataset:prime-rl/eurus-2-rl-da... En Q1 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/rawsh/q1-3B-PRIME
Q1 3B PRIME 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)
Q1 3B PRIME Parameters and Internals
| LLM Name | Q1 3B PRIME |
| Repository 🤗 | https://huggingface.co/rawsh/q1-3B-PRIME |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 13.6 GB |
| Updated | 2025-03-12 |
| Maintainer | rawsh |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | q1 |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Q1 3B PRIME
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...5 3B Instruct Unsloth Bnb 4bit | 32K / 2.4 GB | 158036 | 6 |
| Qwen2.5 3B Unsloth Bnb 4bit | 32K / 2.7 GB | 36007 | 0 |
| TethysAI Base Reasoning | 32K / 6.2 GB | 55 | 0 |
| QwQ LCoT 3B Instruct | 32K / 6.2 GB | 148 | 13 |
| Kyro N1 3B | 32K / 6.2 GB | 1700 | 12 |
| Qwen2.5 3B Reasoner | 32K / 6.2 GB | 22 | 0 |
| Athena 1 3B | 32K / 6.2 GB | 42 | 1 |
| Test StealthThinker | 32K / 6.2 GB | 11 | 0 |
| TBH.AI Base Reasoning | 32K / 6.2 GB | 351 | 1 |
| Predictagrid Sft 3epoch | 32K / 6.2 GB | 117 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than rawsh/q1-3B-PRIME .
Rank the Q1 3B PRIME 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? 44949 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227