Cogito
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size across most standard benchmarks.
What Cogito is for
Cogito is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. Deep Cogito released it in 2025-04 with 5 sizes (3B, 8B, 14B, 32B, 70B) under Apache 2.0, with a 128K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as hybrid reasoning models across all sizes.
Sizes and memory
The 3B needs about 2 GB of weights at Q4_K_M and the 70B about 42 GB, a spread of 40 GB across the family. The catalogue's default pick is 14B. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.
| Size | Weights at Q4_K_M | Recommended VRAM | Smallest card in our guide that holds it |
|---|---|---|---|
| 3B | 2 GB | 3 GB | NVIDIA Jetson Orin Nano 8GB |
| 8B | 6 GB | 9 GB | NVIDIA Jetson Orin Nano 8GB |
| 14B | 9 GB | 14 GB | NVIDIA RTX 3060 12GB |
| 32B | 20 GB | 30 GB | NVIDIA RTX 3090 |
| 70B | 42 GB | 63 GB | Apple M3 Ultra |
Hardware that runs Cogito
Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Cogito at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 8B.
The largest size any of them holds is the 70B at 42 GB, on the Apple M3 Ultra (192 GB at 800 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.
What people use it for
The catalogue lists 4 recorded uses for Cogito: reasoning, agentic, chat, tools. It is tagged reasoning, hybrid, tools, agentic.
Where Cogito sits in the Cogito family
Cogito is the only Cogito entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.
The Apache 2.0 licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.
Context window: 128K
128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.
How to run Cogito locally
Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.
Option 1: Ollama (simplest)
# find the tag for Cogito at ollama.com/library
ollama run <tag>Option 2: Mullama (production)
mullama pull <tag>
mullama run <tag>Option 3: llama.cpp (CLI)
# download a GGUF from Hugging Face, searching for "Cogito GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"Option 4: Python with Mullama or llama-cpp-python
from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))Sources
Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.