The real cost to run granite 4.1 30b

ibm-granite · 28.9B parameters · 131.1K context · commercial OK

granite 4.1 30b — 28.9B params (ibm-granite). Auto-indexed from the Hugging Face Hub (73,001 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run granite 4.1 30b — $0 markup

On your own machine — $0. Runs free locally if you have about 24 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
On your own rented GPU — from $0.49/hr. NVIDIA RTX A6000 48GB at the direct RunPod price (≈ $0.35 a session), $0 markup.
Via your own API key — $0.33/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	28.9B
Context window	131.1K tokens
Recommended quant	Q4_K_M
VRAM to run	~24 GB (at Q4_K_M, 16.4K context)
Download size	~17 GB
License	Commercial use OK

Open the free Spanvero advisor → for the live, interactive math for your exact workload and hardware.

Related models

granite 4.0 h small — 32.2B, ibm-granite
granite 4.1 3b — 3.4B, ibm-granite
granite 4.0 h tiny — 6.9B, ibm-granite
granite 4.0 tiny preview — 6.7B, ibm-granite
granite 3.1 8b instruct — 8.2B, ibm-granite

Browse: More IBM Granite models · All models · Compare