Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Code Conversational Cot En Endpoints compatible Instruct Math Mixtral Moe Region:us Safetensors Sharded Superthoughts Tensorflow
Model Card on HF 🤗: https://huggingface.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427
Superthoughts Lite V2 MoE Llama3.2 Experimental 0427 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)
Superthoughts Lite V2 MoE Llama3.2 Experimental 0427 Parameters and Internals
| LLM Name | Superthoughts Lite V2 MoE Llama3.2 Experimental 0427 |
| Repository 🤗 | https://huggingface.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427 |
| Base Model(s) | |
| Model Size | 3.9b |
| Required VRAM | 7.9 GB |
| Updated | 2025-09-23 |
| Maintainer | Pinkstack |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MixtralForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|begin_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Rank the Superthoughts Lite V2 MoE Llama3.2 Experimental 0427 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? 51626 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124