Ollama · granite3-dense

![An illustration of Ollama holding a beautiful flower with the IBM Rebus logo of the Eye, Bee and M, made by Paul Rand.](https://ollama.com/assets/library/granite3-dense/e2955da9-fee8-45d1-81ed-fe31…

ollama/granite3-dense

![An illustration of Ollama holding a beautiful flower with the IBM Rebus logo of the Eye, Bee and M, made by Paul Rand.](https://ollama.com/assets/library/granite3-dense/e2955da9-fee8-45d1-81ed-fe313f4e83eb)

### Granite dense models

The IBM Granite **2B** and **8B** models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM's initial testing. Granite-8B-Instruct now rivals Llama 3.1 8B-Instruct across both OpenLLM Leaderboard v1 and OpenLLM Leaderboard v2 benchmarks.

**They are designed to support tool-based use cases** and for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.

## Parameter Sizes

**2B:** `ollama run granite3-dense:2b`

**8B:**

`ollama run granite3-dense:8b`

## Supported Languages English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (Simplified)

### Capabilities * Summarization * Text classification * Text extraction * Question-answering * Retrieval Augmented Generation (RAG) * Code related * Function-calling * Multilingual dialog use cases

### Granite mixture of experts models

The Granite mixture of experts models are available in **1B and 3B** parameter sizes designed for **low latency usage**.

[See model page](https://ollama.com/library/granite3-moe)

### Learn more

- **Developers:** IBM Research - **GitHub Repository:** [ibm-granite/granite-3.0-language-models](https://github.com/ibm-granite/granite-3.0-language-models) - **Website**: [Granite Docs](https://www.ibm.com/granite/docs/) - **Release Date**: October 21st, 2024 - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).

Specifications & capabilities

Published model ID
granite3-dense

Deployments & artifacts

1–20 / 33

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
1601931451
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
F16
context window
4000
context window is approximate
true
artifact size bytes
5270488955
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q2_K
context window
4000
context window is approximate
true
artifact size bytes
1011286811
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
4000
context window is approximate
true
artifact size bytes
1400636827
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q3_K_M
context window
4000
context window is approximate
true
artifact size bytes
1294992795
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q3_K_S
context window
4000
context window is approximate
true
artifact size bytes
1173554587
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q4_0
context window
4000
context window is approximate
true
artifact size bytes
1510017211
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q4_1
context window
4000
context window is approximate
true
artifact size bytes
1668352571
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
1601931451
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
4000
context window is approximate
true
artifact size bytes
1521027259
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q5_0
context window
4000
context window is approximate
true
artifact size bytes
1826687931
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q5_1
context window
4000
context window is approximate
true
artifact size bytes
1985023291
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
4000
context window is approximate
true
artifact size bytes
1874037691
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
4000
context window is approximate
true
artifact size bytes
1826687931
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q6_K
context window
4000
context window is approximate
true
artifact size bytes
2163150587
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
2.6B
parameter count
2600000000
parameter count is approximate
true
quantization level
Q8_0
context window
4000
context window is approximate
true
artifact size bytes
2801080955
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
4000
context window is approximate
true
artifact size bytes
4942868123
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
F16
context window
4000
context window is approximate
true
artifact size bytes
16344115003
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q2_K
context window
4000
context window is approximate
true
artifact size bytes
3103600283
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.2B
parameter count
8200000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
4000
context window is approximate
true
artifact size bytes
4349439643
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