What are the hardware requirements for Granite 4.1 30B Fp8?

Granite 4.1 30B Fp8 requires approximately 30.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 4.1 30B Fp8 and how large is it?

Granite 4.1 30B Fp8 is developed by ibm-granite, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Granite 4.1 30B Fp8?

Granite 4.1 30B Fp8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 4.1 30B Fp8 by ibm-granite — VRAM 30.1GB, 128K context

Name: Granite 4.1 30B Fp8
Author: ibm-granite

Granite 4.1 30B Fp8 is an open-source language model by ibm-granite. Features: 30b LLM, VRAM: 30.1GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

Base model:ibm-granite/granite... Base model:quantized:ibm-grani... Compressed-tensors Conversational Endpoints compatible Gguf Granite Granite-4.1 Language Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-4.1-30b-fp8

Granite 4.1 30B Fp8 Benchmarks

LLME Score: 0.29256

^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 4.1 30B Fp8 (ibm-granite/granite-4.1-30b-fp8)

🌟 Advertise your project 🚀

Granite 4.1 30B Fp8 Parameters and Internals

LLM Name	Granite 4.1 30B Fp8
Repository 🤗	https://huggingface.co/ibm-granite/granite-4.1-30b-fp8
Base Model(s)	ibm-granite/granite-4.1-30b ibm-granite/granite-4.1-30b
Model Size	30b
Required VRAM	30.1 GB
Updated	2026-04-30
Maintainer	ibm-granite
Model Type	granite
Model Files	4.9 GB: 1-of-7 4.9 GB: 2-of-7 4.9 GB: 3-of-7 4.9 GB: 4-of-7 4.9 GB: 5-of-7 4.8 GB: 6-of-7 0.8 GB: 7-of-7
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	GraniteForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.6
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352

Best Alternatives to Granite 4.1 30B Fp8

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.1 30B 4bit	128K / 18.1 GB	476	2
Granite 4.1 30B Mxfp8	128K / 29.8 GB	660	2
Granite 4.1 30B Base	128K / 57.8 GB	1280	24
Granite 4.1 30B	128K / 57.8 GB	124	37
Granite 4.1 30B	128K / 57.8 GB	287	0
Unsloth Granite 4.1 30B Mlx	128K / 57.4 GB	49	0
...30B Claude 4.6 Opus Thinking X	128K / 58.6 GB	8	1
...ui Granite 4.1 30B Abliterated	128K / 57.8 GB	162	9

Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-4.1-30b-fp8.

Rank the Granite 4.1 30B 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! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53591 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Granite 4.1 30B Fp8 by ibm-granite

» All LLMs » ibm-granite » Granite 4.1 30B Fp8 URL Share it on

Granite 4.1 30B Fp8 Benchmarks

Granite 4.1 30B Fp8 Parameters and Internals

Best Alternatives to Granite 4.1 30B Fp8

Rank the Granite 4.1 30B Fp8 Capabilities

What open-source LLMs or SLMs are you in search of? 53591 in total.