Skip to content

Head-to-head · Granite

Granite 4.1 30B vs Granite 4.0 H Small

Granite 4.1 30B needs ~19.1 GB at Q4_K_M; Granite 4.0 H Small needs ~20.3 GB. That ~1.2 GB gap decides which hardware runs each; they differ on 0 of the 14 devices below.

Spec Granite 4.1 30B Granite 4.0 H Small
Parameters28.9B32B MoE
Memory at Q4_K_M~19.1 GB~20.3 GB
Context window128k128k
LMArenanot rankednot ranked
LicenseApache-2.0Apache-2.0

Which devices run each

A representative spread across the memory range. Tap a verdict for the full breakdown.

Size at each quantization

Quant Granite 4.1 30B Granite 4.0 H Small
Q2_K 12.1 GB* 13.4 GB*
Q3_K_M 14.1 GB* 15.6 GB*
Q4_K_M 17 GB 18.14 GB
Q5_K_M 20.6 GB* 22.8 GB*
Q6_K 23.7 GB* 26.2 GB*
Q8_0 31 GB 31.91 GB
FP16 58 GB 64.4 GB

* derived from bits-per-weight; unstarred sizes are measured GGUF files.

Bottom line

The larger Granite 4.0 H Small needs ~20.3 GB; Granite 4.1 30B runs on lighter hardware at ~19.1 GB with more headroom and faster responses. Check each against your exact device: what runs Granite 4.1 30B · what runs Granite 4.0 H Small.

More Granite comparisons

FAQ

What is the difference in memory between Granite 4.1 30B and Granite 4.0 H Small?

At Q4_K_M, Granite 4.1 30B needs about 19.1 GB and Granite 4.0 H Small needs about 20.3 GB, a difference of ~1.2 GB.

Should I run Granite 4.1 30B or Granite 4.0 H Small?

Run Granite 4.0 H Small if your hardware has the ~20.3 GB it needs and you want maximum quality; run Granite 4.1 30B (~19.1 GB) for lighter hardware, faster responses, and more memory headroom.

Full breakdowns: Granite 4.1 30B · Granite 4.0 H Small · all models × devices.

Sources

Memory figures are estimates at Q4_K_M, validated 2026-08-03. See methodology.