IBM Granite 4.1 — local AI model by IBM
Written by Jakub Rusinowski · Last updated
IBM's April 29, 2026 release. The 3B and 8B tiers are dense transformers; the 30B tier pivots back to a hybrid Mamba-Transformer (interleaved SSM + attention) design rather than 4.0's MoE. Apache 2.0 licensed, ISO 42001 certified, 128K context (extendable to 512K). All three sizes have official Ollama tags, spanning budget edge hardware to mid-range 24GB GPUs.
Variants
The smallest IBM Granite 4.1 variant needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Granite 4.1 3B → 3B | ~2.6 GB | 128,000 | ollama run granite4.1:3b | |
| Granite 4.1 8B → 8B | ~5.6 GB | 128,000 | ollama run granite4.1:8b | |
| Granite 4.1 30B → 30B | ~18.9 GB | 128,000 | ollama run granite4.1:30b |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run IBM Granite 4.1 locally
Install Ollama, then pull the tag.
ollama run granite4.1:3bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Granite 4.1 3B, Granite 4.1 8B, Granite 4.1 30BRecommended GPU
The cheapest catalogued GPU that runs IBM Granite 4.1 locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run IBM Granite 4.1 on my GPU?
- IBM Granite 4.1 on AMD Radeon RX 9060 XT 8GB
- IBM Granite 4.1 on Apple M1 Max
- IBM Granite 4.1 on Apple M3 Max
- IBM Granite 4.1 on Apple M5 Pro
- IBM Granite 4.1 on Intel Arc B570
- IBM Granite 4.1 on Intel Arc B580
- IBM Granite 4.1 on NVIDIA GeForce RTX 3060 (12GB)
- IBM Granite 4.1 on NVIDIA GeForce RTX 3070
- IBM Granite 4.1 on NVIDIA GeForce RTX 3070 Ti
- IBM Granite 4.1 on NVIDIA GeForce RTX 3080 (10GB)
- IBM Granite 4.1 on NVIDIA GeForce RTX 4060
- IBM Granite 4.1 on NVIDIA GeForce RTX 4070
- IBM Granite 4.1 on NVIDIA GeForce RTX 4070 Super
- IBM Granite 4.1 on NVIDIA GeForce RTX 4070 Ti
- IBM Granite 4.1 on NVIDIA GeForce RTX 5060
- IBM Granite 4.1 on NVIDIA GeForce RTX 5060 Ti 8GB
- IBM Granite 4.1 on NVIDIA GeForce RTX 5070
- IBM Granite 4.1 on NVIDIA L40S
- IBM Granite 4.1 on NVIDIA RTX 6000 Ada Generation
IBM Granite 4.1 — frequently asked questions
How much VRAM does IBM Granite 4.1 need?
IBM Granite 4.1 needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Granite 4.1 3B (3 GB, Q4_K_M); Granite 4.1 8B (6 GB, Q4_K_M); Granite 4.1 30B (19 GB, FP8 (Q4 est. ~12-15GB, unconfirmed)). On Apple Silicon, unified memory counts toward this requirement.
Can I run IBM Granite 4.1 on an RTX 4090 (24 GB)?
Yes — IBM Granite 4.1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for IBM Granite 4.1?
Q4_K_M is the best balance of quality and VRAM for IBM Granite 4.1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run IBM Granite 4.1 with Ollama?
Install Ollama, then run: ollama run granite4.1:3b. This downloads IBM Granite 4.1 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.