granite-4.1-30b
ibm-graniteapache-2.0text

granite-4.1-30b

Updated Sep 27, 2026
Parameters
28.9B
Context
131,072
License
apache-2.0
Q4 GGUF
17.49 GB
Updated
Sep 27, 2026

Q4 GGUF download: ibm-granite/granite-4.1-30b-GGUF - 17.49 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

7.4

AA Index

Coding

10.4

AA Index

Intelligence Index - granite-4.1-30b vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 5.5
57.6
closed
Claude Fable 5.1
53.4
closed
GPT-6 Astra
52.7
closed
Muse Spark 1.3
48.1
closed
GPT-6 Sol
47.5
closed
MiMo-V2.6-Pro
46.3
open
GLM-5.3
44.8
open
granite-4.1-30b
7.4
open

Coding Index comparison

Claude Fable 5.1
81.6
closed
GPT-6 Astra
77.1
closed
Grok 4.6
76.8
closed
GPT-5.6 Terra
76.7
closed
Muse Spark 1.3
76.5
closed
Kimi K3
76.2
open
GLM-5.3
74.8
open
granite-4.1-30b
10.4
open

Benchmark data from Artificial Analysis · updated 2026-09-27.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA Diamond48.1

Source: Artificial Analysis component evals - updated 2026-09-27.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q5_K_M
2 of 4 quantizations fit granite-4.1-30b with real runtime overhead.
Q4_K_M
17 GB
Q5_K_M
21 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve ibm-granite/granite-4.1-30b

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

granite-4.1-30b is a 28.9B-parameter apache-2.0 model from ibm-granite. It scores 7.4 on the Artificial Analysis Intelligence Index. At Q4_K_M it needs roughly 17 GB of VRAM, placing it in the 12–24 GB GPU hardware tier.

Benchmarks

Artificial Analysis Intelligence Index - granite-4.1-30b vs. leading closed models:

ModelIntelligenceCodingGPQA
granite-4.1-30b7.4-48.1
Claude Fable 5.1 (max with fallback)53.4-93.7
GPT-6 Astra (max)52.8-96.1
Claude Opus 5 (max)50.7-93.2
Muse Spark 1.3 (max)48.2-93.5
GPT-5.6 Sol (max)47.1-94.1

Source: Artificial Analysis (2026-09-17).

Popularity

granite-4.1-30b has 688,545 downloads in the last month on HuggingFace and 146 likes.

Frequently asked

Quick answers to common questions

How much VRAM does granite-4.1-30b need?

granite-4.1-30b with 28.9B parameters needs approximately 17 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is granite-4.1-30b better than other ibm-granite models?

granite-4.1-30b has 28.9B parameters with 131,072 context - a strong choice for general use.

What license is granite-4.1-30b under?

granite-4.1-30b is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs granite-4.1-30b well?

With 28.9B parameters, granite-4.1-30b requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for granite-4.1-30b?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~21 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can granite-4.1-30b's context window handle?

granite-4.1-30b supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with granite-4.1-30b?

granite-4.1-30b competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec