// IBM Granite · Text LLM
granite-4.1-30b: VRAM & local deployment
28.9B parameters. About 21.9 GB at 4-bit and 66.2 GB at BF16 with one 8K-token request.
released 2026-04-06licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | IBM · ibm-granite |
|---|---|
| Family / series | IBM Granite · granite-4.1 |
| Type | Text LLM (text-generation) |
| Parameters | 28.9B Source: counted from official safetensors weights |
| Context length | 128K tokens (131,072)max_position_embeddings in config.json |
| Architecture | 64 layers · GQA |
| Released weights | BF16 · 57.7 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-04-06 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 57.7 GB | 66.2 GB | 72.6 GB | 98.4 GB | H100 80GB | Mac 128GB |
| FP8 / INT8 / Q8_0 | 30.7 GB | 36.4 GB | 42.8 GB | 68.6 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 17.5 GB | 21.9 GB | 28.3 GB | 54.1 GB | RTX 5090 32GB | Mac 64GB |
KV cache per request: 8K 2.1 GB · 32K 8.6 GB · 128K 34.4 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- llama.cpp — official GGUF weights
- Ollama — in the official Ollama library · granite4.1:30b
ollama run granite4.1:30b04Official repositories & quantised builds
4 official repo(s) from ibm-granite.
- granite-4.1-30b main
- granite-4.1-30b-base Base
- granite-4.1-30b-GGUF GGUF
- granite-4.1-30b-fp8 FP8
05Other IBM Granite models
All 67 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| granite-4.1-3b · same series | 3.4B | 3.4 GB | 2026-04-06 |
| granite-4.1-8b · same series | 8.79B | 7.7 GB | 2026-04-06 |
| granite-switch-4.1-8b | 8.78B | 7.8 GB | 2026-10-14 |
| granite-switch-4.1-30b | 30B | 22.7 GB | 2026-10-14 |
| granite-speech-5.0-2b | 2.31B | 2.0 GB | 2026-10-07 |
| ensemble-forecasting-with-ibm-granite-time-series | — | — | 2026-10-01 |
| granite-speech-5.0-470m-turboctc-nc | 473M | 0.8 GB | 2026-08-17 |
| granite-4.2-3b | 3.66B | 3.6 GB | 2026-08-07 |
| granite-4.2-8b | 8.79B | 7.7 GB | 2026-08-07 |
| granite-4.2-30b | 29.3B | 22.2 GB | 2026-08-07 |
06Sources
Data checked 2026-05-04. Parameters, context and licence are copied from the official repository; memory figures are our estimates.