Identity
- Status
- active
- Developer ID
ibm-granite/granite-4.2-30b- Released
- Aug 25, 2026
- Version
- Granite 4.2 30B
- License
- apache-2.0
Granite 4.2 30B is IBM's flagship open-weight dense reasoning model with native 128K context, optional 512K long-context extension, flexible thinking modes, and tool calling.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
DeepinfraAvailable | $0.16 | $0.65 | $0.040 | — | Sep 3, 2026 | Provider-reported |
| LMArena Text Arenatext-2026-09-01-011508720696 | 1,362.55 | — | 3,287 | granite-4.2-30b; 95% CI [1351.93384890, 1373.17607017]; votes 3287; rank 177unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
ibm-granite/granite-4.2-30bThis page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | Qwen3.8-27BQwen | cross-developer peerstext | |
| vs | Muse Glimmer 30BMeta | cross-developer peerstext | |
| vs | family variantstext | ||
| vs | Command A ReasoningCohere | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs | gpt-oss-20bOpenai | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs | cross-developer peerstext | ||
| vs | Command A TranslateCohere | cross-developer peerstext |
Questions
Granite 4.2 30B is IBM's flagship open-weight dense reasoning model with native 128K context, optional 512K long-context extension, flexible thinking modes, and tool calling. It is developed by IBM and its current sourced lifecycle status is active.
Granite 4.2 30B's current record lists Text as input and Text as output.
The current record lists a 131,072-token context window and does not report a maximum output length.
Granite 4.2 30B is marked as API-available. The directly sourced provider records currently include Deepinfra and Hugging Face.
The current record lists 29,276,770,304 total parameters and an unknown active parameter count. Its architecture is GraniteForCausalLM.
Granite 4.2 30B's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are code, reasoning, and text.
The lowest directly sourced prices currently attached to Granite 4.2 30B are $0.16 per million input tokens through Deepinfra and $0.65 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Granite 4.2 30B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
No predecessor is recorded. No successor is recorded. Recorded aliases are granite-4.2-30b, Granite 4.2 30B, ibm-granite/granite-4.2-30b, ibm-granite/granite-4.2-30b-fp8, ibm-granite/granite-4.2-30b-GGUF, ibm-granite/granite-4.2-30b-mxfp4, and ibm-granite/granite-4.2-30b-nvfp4.
The current compatible peer set includes Granite 4.2 8B, Granite 4.2 3B, granite-4.1-30b, Qwen3.8-27B, and Muse Glimmer 30B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →