Model library / ibm-granite
Granite Switch 4.1 8B is a modular 8.8 billion-parameter language model that combines a base LLM, decision and safety adapters, and an English speech-to-text encoder.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
The model is described by IBM Granite as a single endpoint that can handle chat, specialised decision-making and speech transcription. It composes the granite-4.1-8b base with two aLoRA adapters, a general-purpose decision adapter and a guardian-core safety adapter, and integrates the Granite Speech 5.0 TurboCTC encoder for English audio input.
In practice the checkpoint weighs 8.8 billion parameters and uses bfloat16 weights. It supports a 131 072-token context window, runs under an Apache-2.0 licence and can be served with HuggingFace Transformers or vLLM. The model has no expert layers and is packaged for deployment as a single vLLM server instance.
Specification
| Repository | ibm-granite/granite-switch-4.1-8b |
| Publisher | ibm-granite |
| Published | 14 October 2026 |
| Architecture | GraniteSwitchForCausalLM |
| Model type | granite_switch |
| Parameters | 8,776,400,896 |
| Layers | 42 |
| Hidden size | 4,096 |
| Attention heads | 32, 8 key/value heads |
| Context length | 131,072 tokens |
| Vocabulary | 100,355 tokens |
| Weight format | bfloat16 |
| Licence | apache-2.0 |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 16.3 GiB | Full precision as released |
| fp8 | 8.2 GiB | 8-bit, near-lossless on most models |
| int4 | 4.1 GiB | 4-bit, smallest footprint |
The cache costs 168 KiB per token at 16-bit, so the full 131,072-token context of one request needs about 21.0 GiB. Concurrency multiplies that number, not the weights.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | 1 | 2.8 GiB | about 17,173 tokens |
| RTX 5090 32GB | 1 | 10.0 GiB | about 62,112 tokens |
| L40S 48GB | 1 | 24.4 GiB | the full 131,072 tokens |
| A100 80GB | 1 | 53.2 GiB | the full 131,072 tokens |
| H100 80GB | 1 | 53.2 GiB | the full 131,072 tokens |
| RTX PRO 6000 96GB | 1 | 67.6 GiB | the full 131,072 tokens |
| H200 141GB | 1 | 108.1 GiB | the full 131,072 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve ibm-granite/granite-switch-4.1-8b \ --max-model-len 16384 \ --gpu-memory-utilization 0.90
Questions
The weights take about 16 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 3 GiB for the key-value cache.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 131,072 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email hello@aiqre.com with the model name and roughly what volume you expect.
Also in the library
Granite Switch 4.1 30B is a modular LLM combining a 30-billion base, decision and guardian adapters, and an English speech-to-tex…
Granite-4.2-30B is a 29.3 billion-parameter decoder-only language model from IBM, designed for reasoning tasks with built-in chai…
Granite-4.2-8B is an 8.8 billion-parameter decoder-only language model from IBM, designed for reasoning-intensive tasks.
Granite-4.2-3B is a 3.7 billion-parameter decoder-only language model with built-in chain-of-thought reasoning, released by IBM u…
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.