Arxiv:2408.13359 Autotrain compatible Granitemoe Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm-research/PowerMoE-3b
PowerMoE 3B 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)
PowerMoE 3B Parameters and Internals
| LLM Name | PowerMoE 3B |
| Repository 🤗 | https://huggingface.co/ibm-research/PowerMoE-3b |
| Model Size | 3b |
| Required VRAM | 13.5 GB |
| Updated | 2025-06-09 |
| Maintainer | ibm |
| Model Type | granitemoe |
| Model Files | |
| Model Architecture | GraniteMoeForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.44.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
| Activation Function | silu |
Best Alternatives to PowerMoE 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Granite 3.1 3B A800m Instruct | 128K / 6.6 GB | 93998 | 24 |
| Granite 3.1 3B A800m Base | 128K / 6.6 GB | 4633 | 7 |
| Granite Guardian 3.2 3B A800m | 128K / 6.6 GB | 1760 | 5 |
| Granite 3.0 3B A800m Instruct | 4K / 6.8 GB | 4107 | 18 |
| Granite 3.0 3B A800m Base | 4K / 13.5 GB | 3669 | 5 |
| PowerMoE 3B | 4K / 13.5 GB | 15341 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than ibm-research/PowerMoE-3b .
Rank the PowerMoE 3B 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? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124