Merged Model Autotrain compatible Base model:bunnycore/llama-3.2... Base model:unsloth/llama-3.2-3... Codegen Conversational Endpoints compatible Instruct Llama Lora Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/bunnycore/Llama-3.2-3B-KodCode-R1
Llama 3.2 3B KodCode R1 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)
Llama 3.2 3B KodCode R1 Parameters and Internals
| LLM Name | Llama 3.2 3B KodCode R1 |
| Repository 🤗 | https://huggingface.co/bunnycore/Llama-3.2-3B-KodCode-R1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 6.4 GB |
| Updated | 2025-07-12 |
| Maintainer | bunnycore |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
Rank the Llama 3.2 3B KodCode R1 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? 50200 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124