Ollama · granite4

<center><img src="https://ollama.com/assets/library/granite3.2/90c5e567-0004-425c-a17a-1b846c2b5d3d" data-canonical-src="https://gyazo.com/eb5c5741b6a9a16c692170a41a49c858.png" width="600" /></center…

ollama/granite4

<center><img src="https://ollama.com/assets/library/granite3.2/90c5e567-0004-425c-a17a-1b846c2b5d3d" data-canonical-src="https://gyazo.com/eb5c5741b6a9a16c692170a41a49c858.png" width="600" /></center>

### Granite 4.0 models

**Granite 4.0 models** are finetuned from their base models using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. They feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

**Please Note:** the 3b, 1b, and 350m model sizes are alternative options for users when mamba-2 support is not yet optimized. Models denoted -h use the hybrid mamba-2 architecture.

#### Parameter Sizes

**350m** ``` ollama run granite4:350m ``` **350m-h** ``` ollama run granite4:350m-h ``` **1b** ``` ollama run granite4:1b ``` **1b-h** ``` ollama run granite4:1b-h ``` **3b (micro)** ``` ollama run granite4:3b ollama run granite4:micro ``` **3b-h (micro-h)** ``` ollama run granite4:3b-h ollama run granite4:micro-h ```

**7b-a1b-h (tiny-h)**

``` ollama run granite4:7b-a1b-h ollama run granite4:tiny-h ```

**32b-a9b-h (small-h)** ``` ollama run granite4:32b-a9b-h ollama run granite4:small-h ```

#### Supported Languages

English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.0 models for languages beyond these languages.

#### Intended Use

This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.

#### Capabilities

- Summarization - Text classification - Text extraction - Question-answering - Retrieval Augmented Generation (RAG) - Code related tasks - Function-calling tasks - Multilingual dialog use cases - Fill-In-the-Middle (FIM) code completions

#### Learn more

- Developers: Granite Team, IBM - Website: [Granite Docs](https://www.ibm.com/granite/docs) - GitHub Repository: [ibm-granite/granite-4.0-language-models](https://github.com/ibm-granite/granite-4.0-language-models) - Release Date: October 2nd, 2025 - License: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)

Specifications & capabilities

Published model ID
granite4

Deployments & artifacts

1–17 / 17

ollama

source id
ollama
execution mode
local
parameter size
1.6B
parameter count
1600000000
parameter count is approximate
true
quantization level
BF16
context window
128000
context window is approximate
true
artifact size bytes
3267419912
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.6B
parameter count
1600000000
parameter count is approximate
true
quantization level
BF16
context window
128000
context window is approximate
true
artifact size bytes
3267419912
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.5B
parameter count
1500000000
parameter count is approximate
true
quantization level
Q8_0
context window
1000000
context window is approximate
true
artifact size bytes
1558945000
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
1.5B
parameter count
1500000000
parameter count is approximate
true
quantization level
Q8_0
context window
1000000
context window is approximate
true
artifact size bytes
1558945000
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.2B
parameter count
32200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
19476640424
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
352.38M
parameter count
352380000
parameter count is approximate
true
quantization level
BF16
context window
32000
context window is approximate
true
artifact size bytes
708457896
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
352.38M
parameter count
352380000
parameter count is approximate
true
quantization level
BF16
context window
32000
context window is approximate
true
artifact size bytes
708457896
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
340.33M
parameter count
340330000
parameter count is approximate
true
quantization level
Q8_0
context window
1000000
context window is approximate
true
artifact size bytes
366214056
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
340.33M
parameter count
340330000
parameter count is approximate
true
quantization level
Q8_0
context window
1000000
context window is approximate
true
artifact size bytes
366214056
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
2099520968
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
1942582952
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
6.9B
parameter count
6900000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
4230994792
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
2099520408
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
2099520968
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.2B
parameter count
3200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
1942582952
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.2B
parameter count
32200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
19476640424
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
6.9B
parameter count
6900000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
1000000
context window is approximate
true
artifact size bytes
4230994792
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace