Hy3 NVFP4 FP8 is an open-source language model by RedHatAI. Features: 172.8b LLM, VRAM: 170.1GB, Context: 256K, License: mit, LLM Explorer Score: 0.32.
8-bit Base model:quantized:tencent/h... Base model:tencent/hy3 Compressed-tensors Conversational Endpoints compatible Hy v3 Llm compressor Region:us Safetensors Sharded Tensorflow Vllm
Model Card on HF 🤗: https://huggingface.co/RedHatAI/Hy3-NVFP4-FP8
Hy3 NVFP4 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)
Hy3 NVFP4 FP8 Parameters and Internals
| LLM Name | Hy3 NVFP4 FP8 |
| Repository 🤗 | https://huggingface.co/RedHatAI/Hy3-NVFP4-FP8 |
| Base Model(s) | |
| Model Size | 172.8b |
| Required VRAM | 170.1 GB |
| Updated | 2026-07-27 |
| Maintainer | RedHatAI |
| Model Type | hy_v3 |
| Model Files | |
| Model Architecture | HYV3ForCausalLM |
| License | mit |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.14.0.dev0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <｜hy_pad:opensource｜> |
| Vocabulary Size | 120832 |
Rank the Hy3 NVFP4 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? 55446 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a