Granite 4.1 30B

Apr 2026
Granite 4.1 30B
Compare in
on
—per task?
$0.10 / $0.25per 1M in / out
—output speed?
131Kcontext

Ranking?

Alternatives?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

History

2 versions
81012Jul 26Release dateAA Intelligence Index 4.3.24.14.2
81012Jul 26Release dateAA Intelligence Index 4.3.24.14.2

FAQ

How much does Granite 4.1 30B cost?›

$0.10 per 1M input tokens and $0.25 per 1M output tokens.

Is Granite 4.1 30B free to use?›

There is no free API; the cheapest paid price is $0.10 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Granite 4.1 30B, and what is it best at?›

#306 of 334 in Chat & Knowledge, #181 of 239 in Coding, #122 of 175 in Agents & Tool Use, #132 of 245 in Writing & Language.

Is Granite 4.1 30B better than NVIDIA Nemotron Nano 12B v2 VL?›

On AA Intelligence Index 4.3.2, Granite 4.1 30B scores 7.4 vs 7.5 — about the same.

How can I use Granite 4.1 30B?›

Through the API of IBM.

What is the context window of Granite 4.1 30B?›

131K tokens.

When was Granite 4.1 30B released? Is there a newer version?›

Released 2026-04-29. It has been superseded by Granite 4.2 30B.

Is Granite 4.1 30B open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Granite 4.1 30B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Granite 4.1 30B read images?›

No, it accepts text only.

What is Granite 4.1 30B?›

Granite 4.1 30B is an open-weights language model from IBM, released Apr 2026.

What are the best alternatives to Granite 4.1 30B?›

Ling 3.0 Flash VL (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).