Skip to main content
Watch: I Built an AI App Without Leaving Databricks

IBM - Dense - verified

Run IBM Granite 4.2 30B locally

IBM Granite 4.2 30B is a 29.3B dense model from IBM with a 131K-token context window, released under Apache 2.0 (commercial use is allowed); the smallest listed download is 16.5 GB, the 4bit MLX build from ibm-granite/granite-4.2-30b-q4-mlx.

Official weights: ibm-granite/granite-4.2-30b

Total params
29.3B
Architecture
Dense
Context
131K
Smallest download
16.5 GB

Fits in

Smallest download at most 85% of memory

Downloads

The official weights and every quantization listed for this model, with file sizes from Hugging Face.

IBM Granite 4.2 30B downloads and file sizes
DownloadFormatSizeRepo
Official weightsBF1658.6 GBibm-granite/granite-4.2-30b
Q4_K_MGGUF17.7 GBibm-granite/granite-4.2-30b-GGUF
Q8_0GGUF31.1 GBibm-granite/granite-4.2-30b-GGUF
4bitSmallest listedMLX16.5 GBibm-granite/granite-4.2-30b-q4-mlx

GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.

Run it

Copied verbatim from the page linked under each command. Server commands from model cards often assume a multi-GPU node; check the flags before you run them.

Ollama

Terminal
ollama run granite4.2:30b

Source: ollama.com/library/granite4.2:30b

vLLM

Terminal
vllm serve ibm-granite/granite-4.2-30b \
    --served-model-name granite-4.2-30b \
    --dtype bfloat16 \
    --max-model-len 131072 \
    --reasoning-parser granite_thinking_parser \
    --reasoning-parser-plugin ./granite_thinking_parser.py \
    --tool-call-parser qwen3_coder \
    --enable-auto-tool-choice

Source: huggingface.co/ibm-granite/granite-4.2-30b

SGLang

Terminal
python3 -m sglang.launch_server \
    --model-path ibm-granite/granite-4.2-30b \
    --dtype bfloat16 \
    --context-length 131072 \
    --reasoning-parser auto \
    --tool-call-parser auto

Source: huggingface.co/ibm-granite/granite-4.2-30b

Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.

License

License
Apache 2.0apache-2.0
Commercial use
Commercial use: YesCommercial use is allowed.
Gated download
No. The files download directly.

Worth knowing

Flagship dense reasoning model of Granite 4.2, with thinking on by default and a 128K native context that the card says extends to 512K.

Released (per the model card).

FAQ

How big is the IBM Granite 4.2 30B download?

The official BF16 weights in ibm-granite/granite-4.2-30b are 58.6 GB. The smallest listed download is 16.5 GB, the 4bit MLX build from ibm-granite/granite-4.2-30b-q4-mlx. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.

Can I use IBM Granite 4.2 30B commercially?

IBM Granite 4.2 30B is released under Apache 2.0, and commercial use is allowed. The license text is at https://www.apache.org/licenses/LICENSE-2.0.

How much memory do I need for IBM Granite 4.2 30B?

By this directory's rule of thumb it fits in 24 GB and up: the smallest listed download, 16.5 GB, is at most 85% of 24 GB, which leaves room for the context and the operating system.

How do I run IBM Granite 4.2 30B with Ollama?

Run "ollama run granite4.2:30b", as shown at https://ollama.com/library/granite4.2:30b. The Ollama library lists the granite4.2:30b tag at 18GB.

What is the context length of IBM Granite 4.2 30B?

131,072 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.

Sources

Last verified from the pages below.

Newsletter

New open weights, every week

One email per week. New model releases, open-weight drops and what they mean for what you build.

Keep exploring

Best local AI models

Our curated picks by hardware tier, with benchmarks and the reasoning.

Model API pricing and specs

First-party prices per 1M tokens when you would rather call an API.

AI benchmark leaderboards

Sourced scores, for when you need to compare quality.

Setup guides

Point your coding tools at the model you picked.