Neutrino 8B is an open-source language model by FermionResearch. Features: 8b LLM, VRAM: 3.9GB, License: apache-2.0, LLM Explorer Score: 0.46.
Base model:quantized:qwen/qwen... Base model:qwen/qwen3-8b Conversational Endpoints compatible Gguf Quantization Region:us Sub-2-bit Ternary Trtc Trtc v4
Model Card on HF 🤗: https://huggingface.co/FermionResearch/Neutrino-8B
Neutrino 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)
Neutrino 8B Parameters and Internals
| LLM Name | Neutrino 8B |
| Repository 🤗 | https://huggingface.co/FermionResearch/Neutrino-8B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 3.9 GB |
| Updated | 2026-07-30 |
| Maintainer | FermionResearch |
| Model Type | trtc_v4 |
| Model Files | |
| Model Architecture | TrtcV4ForCausalLM |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Transformers Version | 5.14.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |
Rank the Neutrino 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? 55501 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