Granite Switch 4.1 8B Preview is an open-source language model by ibm-granite. Features: 8b LLM, VRAM: 19.1GB, Context: 128K, License: apache-2.0.
Conversational Endpoints compatible Granite-4.1 Granite-switch Granite switch Language Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview
Granite Switch 4.1 8B Preview Parameters and Internals
| LLM Name | Granite Switch 4.1 8B Preview |
| Repository 🤗 | https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview |
| Model Size | 8b |
| Required VRAM | 19.1 GB |
| Updated | 2026-05-07 |
| Maintainer | ibm-granite |
| Model Type | granite_switch |
| Model Files | |
| Model Architecture | GraniteSwitchForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.5.4 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 100364 |
| Errors | replace |
Rank the Granite Switch 4.1 8B Preview 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? 53518 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