granite-4.1-30b
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
IBM Granite · General · Granite 4.1
Granite 4.1 30B: Specs, GPU requirements, hosting & deployment
Granite 4.1 30B is a recent General release in the IBM Granite family, certified from its immutable official source revision.
Total parameters28.9B
Active parametersDense model
Context window131,072 tokens
Release statusRecent · Recent
ArchitectureGraniteForCausalLM
ModalitiesText
Licenseapache-2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-04-06
Architecture, strengths and use cases
Granite 4.1 30B is an official self-hostable IBM release in the IBM Granite General track. It uses GraniteForCausalLM, carries 28.9B, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Granite 4.1 30B uses GraniteForCausalLM with 28.9B. The stored architecture profile records 64 layers, hidden width 4096, 32 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified GraniteForCausalLM architecture
131,072 token certified context
Official BF16 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory55.45 GB
KV cache2 GB
Runtime overhead15.06 GB
Total with safety margin89.91 GB
Recommended best value
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
70.09 GB headroom · Available
USD 1,830 / monthLowest-cost viable
4× NVIDIA L4 24GB
96 GB total VRAM · pcie
6.09 GB headroom · Available
USD 1,000 / monthHighest performance
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
70.09 GB headroom · Available
USD 1,830 / monthLicense and self-hosting considerations
The full 28.9B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Granite 4.1 30B is published under apache-2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
Granite 4.2 30B, Granite 4.2 8B, Granite 4.2 3B
Release timeline
ibm/granite/granite-4-1-30b
Source details
Source revision: c9d5fa2930a611bb481573dc233b242ee8f2b45f60d32c68ce6bb1bd80e1be0c
Frequently asked questions
How much VRAM does Granite 4.1 30B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Granite 4.1 30B?
Certified upstream runtime evidence is available for transformers.
Can Granite 4.1 30B be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
Official references
Last verified: 2026-09-03