Granite Guardian 3.2 8B Factuality Detection is an open-source language model by ibm-granite. Features: 8b LLM, VRAM: 16.4GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.24.
Arxiv:2412.07724 Arxiv:2502.18573 Base model:finetune:ibm-granit... Base model:ibm-granite/granite... Conversational Deploy:azure En Endpoints compatible Granite Instruct Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-guardian-3.2-8b-factuality-detection
Granite Guardian 3.2 8B Factuality Detection 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)
Granite Guardian 3.2 8B Factuality Detection Parameters and Internals
| LLM Name | Granite Guardian 3.2 8B Factuality Detection |
| Repository 🤗 | https://huggingface.co/ibm-granite/granite-guardian-3.2-8b-factuality-detection |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.4 GB |
| Updated | 2026-04-17 |
| Maintainer | ibm-granite |
| Model Type | granite |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GraniteForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.50.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 49155 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Granite Guardian 3.2 8B Factuality Detection
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Granite 3.1 8B Instruct | 128K / 16.4 GB | 43469 | 168 |
| Granite 3.1 8B Reasoning | 128K / 16.4 GB | 11 | 1 |
| Granite 3.1 8B Instruct | 128K / 16.4 GB | 72 | 1 |
| Granite 3.2 8B Instruct | 128K / 16.4 GB | 4357 | 87 |
| Granite 3.3 8B Instruct | 128K / 16.4 GB | 69232 | 144 |
| Granite 3.3 8B Instruct FP8 | 128K / 8.4 GB | 4217 | 2 |
| Granite 3.3 8B Math Prm V2 | 128K / 16.4 GB | 65 | 14 |
| Granite 3.3 8B Qiskit | 128K / 16.4 GB | 62 | 7 |
| ...ranite 3.2 8B Instruct Preview | 128K / 16.4 GB | 36 | 69 |
| Granite 3.2 8B Instruct | 128K / 21.5 GB | 36 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-guardian-3.2-8b-factuality-detection .
Rank the Granite Guardian 3.2 8B Factuality Detection 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? 52996 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