Ollama · cogito

<img src="/assets/library/cogito/44ceefc5-6a71-4d18-958e-21d45d309b18" width="320" /> The Cogito v1 Preview LLMs are instruction tuned generative models (text in/text out). All models are released un…

ollama/cogito

<img src="/assets/library/cogito/44ceefc5-6a71-4d18-958e-21d45d309b18" width="320" />

The Cogito v1 Preview LLMs are instruction tuned generative models (text in/text out). All models are released under an open license for commercial use.

- Cogito models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models). - The LLMs are trained using **Iterated Distillation and Amplification (IDA)** - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement. - The models have been optimized for coding, STEM, instruction following and general helpfulness, and have significantly higher multilingual, coding and tool calling capabilities than size equivalent counterparts. - In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks. - Each model is trained in over 30 languages and supports a context length of 128k.

## Extended thinking

To enable extended thinking, include `Enable deep thinking subroutine.` in the system prompt:

``` /set system """Enable deep thinking subroutine.""" ```

Or via the API:

``` curl http://localhost:11434/api/chat -d '{ "model": "cogito", "messages": [ { "role": "system", "content": "Enable deep thinking subroutine." }, { "role": "user", "content": "How many letter Rs are in the word Strawberry?" } ] }' ```

## Sizes

#### 3B

``` ollama run cogito:3b ```

#### 8B

``` ollama run cogito:8b ```

#### 14B

``` ollama run cogito:14b ```

#### 32B

``` ollama run cogito:32b ```

#### 70B

``` ollama run cogito:70b ```

## Benchmarks

### Smaller models - 3B and 8B

#### 3B performance ![3b.webp](/assets/library/cogito/b3f444f7-91a6-4bd4-a395-a515060752b9)

#### 8B performance ![8b.webp](/assets/library/cogito/e2cc899a-0f9f-48c5-a530-e941576bd67a)

#### 3B tool calling ![3b-toolcalling.webp](/assets/library/cogito/53992b0e-9226-4fff-ba70-9ffd7f980f2f)

### Medium models - 14B and 32B

#### 14B ![14b.webp](/assets/library/cogito/c32b8f91-3b00-457a-ad54-feab83d1decf)

#### 32B ![32b.webp](/assets/library/cogito/bc5ea441-1fb8-4bf6-b4de-9093b0e74426)

### Larger models - 70B ![70b.webp](/assets/library/cogito/139c3df7-bdc5-4497-aa51-cddb7eccaca9)

## References

[Blog post](https://www.deepcogito.com/research/cogito-v1-preview)

[Hugging Face](https://huggingface.co/collections/deepcogito/cogito-v1-preview-67eb105721081abe4ce2ee53)

Specifications & capabilities

Published model ID
cogito

Deployments & artifacts

1–20 / 20

ollama

source id
ollama
execution mode
local
parameter size
14.8B
parameter count
14800000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
8985290822
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
14.8B
parameter count
14800000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
29539549958
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
14.8B
parameter count
14800000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
8985290822
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
14.8B
parameter count
14800000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
15697261958
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.8B
parameter count
32800000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
19848516422
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.8B
parameter count
32800000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
65527803398
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.8B
parameter count
32800000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
19848516422
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.8B
parameter count
32800000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
34816548998
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.6B
parameter count
3600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
2241013158
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.6B
parameter count
3600000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
7221702054
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.6B
parameter count
3600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
2241013158
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.6B
parameter count
3600000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
3840535974
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
42520410444
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
141117929804
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
42520410444
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
70.6B
parameter count
70600000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
74975066444
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
4920747535
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
4920747535
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
8540784143
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
4920747535
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