Nemotron3 8B is an open-source language model by thhaus. Features: 8b LLM, VRAM: 17.1GB, Context: 4K, LLM Explorer Score: 0.16.
Model Card on HF 🤗: https://huggingface.co/thhaus/nemotron3-8b
Nemotron3 8B 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)
Nemotron3 8B Parameters and Internals
| LLM Name | Nemotron3 8B |
| Repository 🤗 | https://huggingface.co/thhaus/nemotron3-8b |
| Model Size | 8b |
| Required VRAM | 17.1 GB |
| Updated | 2026-04-02 |
| Maintainer | thhaus |
| Model Type | nemotron |
| Model Files | |
| Model Architecture | NemotronForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.44.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Nemotron3 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Minitron 8B Base | 4K / 16.5 GB | 14165 | 69 |
Note: green Score (e.g. "73.2") means that the model is better than thhaus/nemotron3-8b .
Rank the Nemotron3 8B 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a