Skip to content

Cogito 70B

by Deep Cogito · cogito family

70B

parameters

text-generation code-generation reasoning math multilingual

Cogito 70B is the flagship model from Deep Cogito, built on a Llama 70B base with significantly enhanced reasoning capabilities. It achieves top-tier benchmark results while maintaining the MIT license for maximum flexibility. With an MMLU score of 86.0 and a 131K context window, Cogito 70B is one of the strongest open-weight reasoning models available, though it requires high-end hardware with at least 43GB of VRAM for the Q4 quantization.

Quick Start with Ollama

ollama run 70b-q4_K_M
Resources Ollama Hugging Face Official Page
Creator Deep Cogito
Parameters 70B
Architecture transformer-decoder
Context 128K tokens
Released Mar 24, 2025
License MIT
Ollama cogito:70b

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 35 GB 43 GB 70b-q4_K_M
Q8_0 70 GB 76 GB 70b-q8_0

Compatible Hardware

Q4_K_M requires 43 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~19 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~19 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~19 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~13 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~13 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~13 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~45 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~9 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~6 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~13 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~13 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~13 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns (tight)~22 tok/s
NVIDIA RTX A600048 GBgpuRuns (tight)~18 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns (tight)~22 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns (tight)~6 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns (tight)~9 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns (tight)~6 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns (tight)~13 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns (tight)~10 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns (tight)~6 tok/s
Mac Studio M4 Max 36GB36 GBmacCPU Offload~4 tok/s
MacBook Pro M3 Pro 36GB36 GBmacCPU Offload~1 tok/s
MacBook Pro M5 Max 36GB36 GBmacCPU Offload~3 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuCPU Offload~5 tok/s
NVIDIA GeForce RTX 509032 GBgpuCPU Offload~13 tok/s
iMac M4 32GB32 GBmacCPU Offload~1 tok/s
Mac mini M4 32GB32 GBmacCPU Offload~1 tok/s
MacBook Air M4 32GB32 GBmacCPU Offload~1 tok/s
MacBook Air M5 32GB32 GBmacCPU Offload~1 tok/s
MacBook Pro M5 32GB32 GBmacCPU Offload~1 tok/s
76 hardware device(s) cannot run this model at Q4_K_M.

Benchmark Scores

86.0
mmlu