Arxiv:2504.03624 Arxiv:2505.00949 Conversational En Endpoints compatible Nvidia Pytorch Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Nemotron-H-8B-Reasoning-128K-FP8
Nemotron H 8B Reasoning 128K FP8 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)
Nemotron H 8B Reasoning 128K FP8 Parameters and Internals
| LLM Name | Nemotron H 8B Reasoning 128K FP8 |
| Repository 🤗 | https://huggingface.co/nvidia/Nemotron-H-8B-Reasoning-128K-FP8 |
| Model Size | 8b |
| Required VRAM | 9.2 GB |
| Updated | 2026-03-10 |
| Maintainer | nvidia |
| Model Type | nemotron_h |
| Model Files | |
| Supported Languages | en |
| Model Architecture | NemotronHForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Nemotron H 8B Reasoning 128K FP8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nemotron H 8B Reasoning 128K | 128K / 16.2 GB | 623 | 22 |
| Nemotron H 8B Base 8K | 8K / 16.2 GB | 27213 | 51 |
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Nemotron-H-8B-Reasoning-128K-FP8 .
Rank the Nemotron H 8B Reasoning 128K FP8 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