Granite 4.2 30b
5367°
ibm-granite | 131,072 token context | $0.16/M input, $0.65/M output. Granite-4.2-30B is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across reasoning-intensive tasks by leveraging built-in ... chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.
Guides for this model
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Granite 4.2 30B is IBM's flagship reasoning model in the Granite 4.2 family, built around chain-of-thought and offered with three thinking modes so you can trade depth for speed on a per-query basis. At $0.16 per million input tokens it sits well below most frontier reasoning models. It suits developers and analysts who need serious reasoning without a serious bill.
Known for
- Built-in chain-of-thought reasoning as a first-class feature, not a prompt trick.
- Three thinking modes: full, non-thinking, and low-effort for latency control.
- Competitive pricing at $0.16/M input and $0.65/M output.
- 131,072-token context window for longer documents and multi-step tasks.
Watch out for
- Weights are not public; you are tied to IBM's API with no option to self-host.
- IBM has not published benchmark numbers, so independent comparisons are hard to make.
- Output at $0.65/M is reasonable but reasoning-heavy queries generate long outputs fast.
Prompts to try
Multi-step logic puzzle
Five colleagues — Ana, Ben, Cara, Dan and Eve — each work in a different department: HR, Finance, Legal, Engineering and Marketing. Ana is not in HR or Finance. Ben is in Legal. Cara is not in Marketing. Dan is in Engineering. Work out which department each person is in, showing your reasoning step by step.
Causal analysis task
A software team ships a new release on Monday. By Wednesday, error rates have doubled, average response time has increased by 40%, and one specific API endpoint accounts for 80% of the new errors. Walk through the most likely causes in order of probability, the evidence you would collect to confirm each, and the fastest safe rollback path.
Structured data extraction
Extract all financial obligations from the following contract clause and return them as a JSON array. Each object should have: party, obligation_type, amount_or_rate, due_date, and penalty_for_breach. Clause: 'Acme Corp shall pay Vendor a monthly retainer of $12,000 due on the first of each month. Late payments incur a 1.5% monthly interest charge. A one-time setup fee of $5,000 is due within 30 days of contract signing.'
Compare with
- Qwen3 30B A3B Thinking 2507API-only model81,920 token context · $0.20/M input, $2.40/M output
- Gemini 2.5 Pro Preview 06-05API-only model1,048,576 token context · $1.25/M input, $10.00/M output
- o3 ProAPI-only model200,000 token context · $20.00/M input, $80.00/M output
- Ling 3.0 Flash FinAPI-only model262,144 token context · $0.04/M input, $0.12/M output
More text models from ibm-granite
Questions people ask
- Can I run Granite 4.2 30B locally?
- No. IBM has not released open weights for this model, so it is API-only and cannot be self-hosted.
- What does it cost and how long is the context?
- Pricing is $0.16 per million input tokens and $0.65 per million output tokens, with a 131,072-token context window.
- What are the three thinking modes and when should I use them?
- Full thinking is the default and gives the deepest reasoning; non-thinking skips the chain-of-thought for faster, cheaper responses; low-effort sits in between, useful when you want some reasoning without the full latency hit.
Captain's verdictA genuinely affordable reasoning model with useful latency controls — worth a look if IBM's API lock-in does not bother you.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Granite 4.2 30b is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153