Skip to content
localmodel.run

Text model · Granite

Granite 4.0 H Small requirements

Granite family · 32B params (Mixture-of-Experts, 9B active) · released Oct 2025 · 1.2M Ollama pulls. Minimum to run at Q4_K_M: Nvidia GeForce RTX 4090 (24GB).

LicenseApache-2.0· Commercial OK↓ 422.4K/mo♥ 308on HuggingFace
Q4_K_M
18.23 GB
Q8_0
31.91 GB
Total @ Q4 (4k)
~20.4 GB
Context
128 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K13.4 GB est
Q3_K_M15.6 GB est
Q4_K_M (default)18.23 GB
Q5_K_M22.8 GB est
Q6_K26.2 GB est
Q8_031.91 GB
FP1664 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run granite4:small-h
llama.cpp
$ llama-cli -hf unsloth/granite-4.0-h-small-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/granite-4.0-h-small-GGUF

Which devices can run Granite 4.0 H Small?

FAQ

How much VRAM or RAM does Granite 4.0 H Small need?

At Q4_K_M, Granite 4.0 H Small needs about 20.4 GB (weights ~18.23 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~34.1 GB.

Can Granite 4.0 H Small run on a laptop?

Granite 4.0 H Small is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Is Granite 4.0 H Small cheaper to run because it is a MoE model?

It is faster, not lighter. Granite 4.0 H Small activates only 9B of 32B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 32B.

Can I use Granite 4.0 H Small commercially?

Yes. Granite 4.0 H Small is licensed Apache-2.0, which permits commercial use.

IBM Granite 4.0 H Small, hybrid Mamba/transformer MoE (32B total, 9B active), 128K context. Q4_K_M and Q8_0 sizes from the unsloth GGUF repo, matched to the Ollama granite4:small-h tag.

Sources

Memory figures are estimates. See methodology.