ibm-granite / text-generation updated 3 months ago

granite-4.1-3b-GGUF

> [!NOTE] > This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite .safetensors model. > > Please reference the base model's full model card here: > https://huggingface.co/ibm-granite/granite-4.1-3b

Params
Context
Downloads 30d
170 K
Likes
10
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days
236 K170 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
granite-4.1-3b-Q2_K.gguf Q2_K 1.4 GB 2.0 GB ✅ Runs comfortably
granite-4.1-3b-Q3_K_S.gguf Q3_K_S 1.6 GB 2.2 GB ✅ Runs comfortably
granite-4.1-3b-Q3_K_M.gguf Q3_K_M 1.7 GB 2.4 GB ✅ Runs comfortably
granite-4.1-3b-Q3_K_L.gguf Q3_K_L 1.9 GB 2.6 GB ✅ Runs comfortably
granite-4.1-3b-Q4_0.gguf Q4_0 2.0 GB 2.7 GB ✅ Runs comfortably
granite-4.1-3b-Q4_K_S.gguf Q4_K_S 2.0 GB 2.7 GB ✅ Runs comfortably
granite-4.1-3b-Q4_K_M.gguf Q4_K_M 2.1 GB 2.8 GB ✅ Runs comfortably
granite-4.1-3b-Q4_1.gguf Q4_1 2.2 GB 2.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_0
$ ollama run granite-4-1-3b-gguf

# pin the quantization explicitly
$ ollama run granite-4-1-3b-gguf-q4_0
est. VRAM 2.7 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2026-04-16
Base model
granite-4.1-3b
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.