DeepCogito/Mixture of Experts

DCogito v2 109B MoE

Name: Cogito v2 109B MoE
Author: DeepCogito

The Cogito v2 LLMs are instruction tuned generative models. All models are released under an open license for commercial use.

chatreasoningtool_use

109B

Parameters (17B active)

256K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2025-09-10

Layers

KV Heads

Head Dim

128

Family

cogito

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	32.9 GB	low
IQ2_M	2.93	40.4 GB	low
Q2_K	3.16	43.5 GB	low
IQ3_XXS	3.25	44.8 GB	low
IQ3_XS	3.5	48.2 GB	low
Q3_K_S	3.64	50.1 GB	low
IQ3_M	3.76	51.7 GB	low
Q3_K_M	4	55.0 GB	low
Q3_K_L	4.3	59.1 GB	moderate
IQ4_XS	4.46	61.3 GB	moderate
Q4_K_S	4.67	64.1 GB	moderate
Q4_K_M	4.89	67.1 GB	good
Q5_K_S	5.57	76.4 GB	good
Q5_K_M	5.7	78.2 GB	good
Q6_K	6.56	89.9 GB	excellent
Q8_0	8.5	116.3 GB	lossless
FP16	16	218.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN COGITO V2 109B MOE NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run cogito:109b-q4_K_M

Tag may need adjustment — check ollama.com/library/cogito for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware