4bit Autotrain compatible Conversational En Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/ReasoningCore-3B-Instruct-r01-Reflect
ReasoningCore 3B Instruct R01 Reflect Benchmarks
MMLU Pro: 23.82
GPQA: 3.13
MUSR: 3.09
BBH: 22.27
IFEval: 73.35 vs 88 (so35)-16.6%
MATH Lvl 5: 15.41
LLME Score: 0.28886
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)
ReasoningCore 3B Instruct R01 Reflect Parameters and Internals
| LLM Name | ReasoningCore 3B Instruct R01 Reflect |
| Repository 🤗 | https://huggingface.co/EpistemeAI/ReasoningCore-3B-Instruct-r01-Reflect |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-05-30 |
| Maintainer | EpistemeAI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Gated Model | Yes |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | proprietary |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to ReasoningCore 3B Instruct R01 Reflect
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ama Llama 3.2 3B Instruct FP16 | 128K / 6.5 GB | 1438358 | 0 |
| ...2 3B Instruct Unsloth Bnb 4bit | 128K / 2.4 GB | 138117 | 10 |
| ReasoningCore 3B 0 | 128K / 6.5 GB | 247 | 2 |
| Llama32 3B En Emo 2000 Stp | 128K / 2.2 GB | 37 | 0 |
| Llama32 3B En Emo 300 Stp | 128K / 2.2 GB | 5 | 0 |
| Llama32 3B En Emo 1000 Stp | 128K / 2.2 GB | 5 | 0 |
| Llama32 3B En Emo 5000 Stp | 128K / 2.2 GB | 5 | 0 |
| ....1 Llama 3.2 3B It Grpo 250404 | 128K / 6.5 GB | 1040 | 61 |
| Security Llama3.2 3B | 128K / 6.5 GB | 8 | 0 |
| ....1 Pretrained Unsloth Bnb 4bit | 128K / 2.5 GB | 2746 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/ReasoningCore-3B-Instruct-r01-Reflect .
Rank the ReasoningCore 3B Instruct R01 Reflect 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? 49801 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124