Autotrain compatible Base model:meta-llama/llama-3.... Base model:quantized:meta-llam... Conversational Endpoints compatible Gguf Instruct Llama Llama-3.2 Q4 Quantized Region:us Safetensors Sharded Tensorflow Thought-chain
Model Card on HF 🤗: https://huggingface.co/ericflo/Llama-3.2-3B-COT
Llama 3.2 3B COT 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 COT Parameters and Internals
| LLM Name | Llama 3.2 3B COT |
| Repository 🤗 | https://huggingface.co/ericflo/Llama-3.2-3B-COT |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-03-12 |
| Maintainer | ericflo |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3.2 3B COT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 MEDIT 3B O1 | 128K / 6.5 GB | 496 | 12 |
| ReWiz Llama 3.2 3B | 128K / 6.5 GB | 695 | 3 |
| Gunny | 128K / 6.5 GB | 55 | 0 |
| ...2 3B Instruct Unsloth Bnb 4bit | 128K / 2.4 GB | 265318 | 6 |
| Llama32 3B En Emo 2000 Stp | 128K / 2.2 GB | 42 | 0 |
| Llama32 3B En Emo 300 Stp | 128K / 2.2 GB | 30 | 0 |
| ReasoningCore 3B 0 | 128K / 6.5 GB | 215 | 2 |
| Llama32 3B En Emo 1000 Stp | 128K / 2.2 GB | 13 | 0 |
| ...ngCore 3B Instruct R01 Reflect | 128K / 6.5 GB | 28 | 1 |
| Llama32 3B En Emo 5000 Stp | 128K / 2.2 GB | 13 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ericflo/Llama-3.2-3B-COT .
Rank the Llama 3.2 3B COT 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? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227