Skip to content

Cogito 8B

by Deep Cogito · cogito family

8B

parameters

text-generation code-generation reasoning math

Cogito 8B is the compact variant from Deep Cogito's first model family, built on a Llama 8B base with enhanced reasoning capabilities. It supports a 131K context window and excels at mathematical problem-solving and code generation tasks. As the smallest model in the Cogito lineup, the 8B variant offers an accessible entry point for local reasoning-focused inference on consumer hardware with 8GB or more of VRAM.

Quick Start with Ollama

ollama run 8b-q4_K_M
Resources Ollama Hugging Face Official Page
Creator Deep Cogito
Parameters 8B
Architecture transformer-decoder
Context 128K tokens
Released Mar 24, 2025
License MIT
Ollama cogito:8b

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 5 GB 7.5 GB 8b-q4_K_M
Q8_0 8.5 GB 11 GB 8b-q8_0
F16 16 GB 19.5 GB 8b-fp16

Compatible Hardware

Q4_K_M requires 7.5 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~109 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~107 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~109 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~73 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~73 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~73 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~256 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~53 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~36 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~73 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~73 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~73 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns~128 tok/s
NVIDIA RTX A600048 GBgpuRuns~102 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns~128 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns~36 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns~53 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns~36 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns~73 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns~55 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns~36 tok/s
Mac Studio M4 Max 36GB36 GBmacRuns~73 tok/s
MacBook Pro M3 Pro 36GB36 GBmacRuns~20 tok/s
MacBook Pro M5 Max 36GB36 GBmacRuns~55 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuRuns~96 tok/s
NVIDIA GeForce RTX 509032 GBgpuRuns~239 tok/s
iMac M4 32GB32 GBmacRuns~16 tok/s
Mac mini M4 32GB32 GBmacRuns~16 tok/s
MacBook Air M4 32GB32 GBmacRuns~16 tok/s
MacBook Air M5 32GB32 GBmacRuns~16 tok/s
MacBook Pro M5 32GB32 GBmacRuns~16 tok/s
AMD Radeon RX 7900 XTX24 GBgpuRuns~128 tok/s
NVIDIA GeForce RTX 3090 Ti24 GBgpuRuns~134 tok/s
NVIDIA GeForce RTX 309024 GBgpuRuns~125 tok/s
NVIDIA GeForce RTX 409024 GBgpuRuns~134 tok/s
NVIDIA RTX A500024 GBgpuRuns~102 tok/s
iMac M3 24GB24 GBmacRuns~13 tok/s
Mac mini M2 24GB24 GBmacRuns~13 tok/s
Mac mini M4 Pro 24GB24 GBmacRuns~36 tok/s
MacBook Air M2 24GB24 GBmacRuns~13 tok/s
MacBook Air M4 24GB24 GBmacRuns~16 tok/s
MacBook Air M5 24GB24 GBmacRuns~16 tok/s
MacBook Pro M4 Pro 24GB24 GBmacRuns~36 tok/s
MacBook Pro M5 24GB24 GBmacRuns~16 tok/s
MacBook Pro M5 Pro 24GB24 GBmacRuns~36 tok/s
AMD Radeon RX 7900 XT20 GBgpuRuns~107 tok/s
NVIDIA RTX 4000 Ada Generation20 GBgpuRuns~48 tok/s
MacBook Pro M3 Pro 18GB18 GBmacRuns~20 tok/s
AMD Radeon RX 6800 XT16 GBgpuRuns~68 tok/s
AMD Radeon RX 6900 XT16 GBgpuRuns~68 tok/s
AMD Radeon RX 7800 XT16 GBgpuRuns~83 tok/s
AMD Radeon RX 9060 XT 16GB16 GBgpuRuns~72 tok/s
AMD Radeon RX 9070 XT16 GBgpuRuns~87 tok/s
AMD Radeon RX 907016 GBgpuRuns~72 tok/s
Intel Arc A77016 GBgpuRuns~75 tok/s
NVIDIA GeForce RTX 4060 Ti 16GB16 GBgpuRuns~38 tok/s
NVIDIA GeForce RTX 4070 Ti Super16 GBgpuRuns~90 tok/s
NVIDIA GeForce RTX 4080 Super16 GBgpuRuns~98 tok/s
NVIDIA GeForce RTX 408016 GBgpuRuns~96 tok/s
NVIDIA GeForce RTX 5060 Ti 16GB16 GBgpuRuns~60 tok/s
NVIDIA GeForce RTX 5070 Ti16 GBgpuRuns~119 tok/s
NVIDIA GeForce RTX 508016 GBgpuRuns~128 tok/s
NVIDIA RTX A400016 GBgpuRuns~60 tok/s
iMac M1 16GB16 GBmacRuns~9 tok/s
iMac M4 16GB16 GBmacRuns~16 tok/s
Mac mini M1 16GB16 GBmacRuns~9 tok/s
Mac mini M4 16GB16 GBmacRuns~16 tok/s
MacBook Air M2 16GB16 GBmacRuns~13 tok/s
MacBook Air M3 16GB16 GBmacRuns~13 tok/s
MacBook Air M4 16GB16 GBmacRuns~16 tok/s
MacBook Air M5 16GB16 GBmacRuns~16 tok/s
MacBook Pro M1 16GB16 GBmacRuns~9 tok/s
MacBook Pro M2 Pro 16GB16 GBmacRuns~27 tok/s
MacBook Pro M5 16GB16 GBmacRuns~16 tok/s
AMD Radeon RX 6700 XT12 GBgpuRuns~51 tok/s
AMD Radeon RX 7700 XT12 GBgpuRuns~58 tok/s
Intel Arc B58012 GBgpuRuns~61 tok/s
NVIDIA GeForce RTX 3060 12GB12 GBgpuRuns~48 tok/s
NVIDIA GeForce RTX 3080 12GB12 GBgpuRuns~122 tok/s
NVIDIA GeForce RTX 4070 Super12 GBgpuRuns~67 tok/s
NVIDIA GeForce RTX 4070 Ti12 GBgpuRuns~67 tok/s
NVIDIA GeForce RTX 407012 GBgpuRuns~67 tok/s
NVIDIA GeForce RTX 507012 GBgpuRuns~90 tok/s
NVIDIA GeForce GTX 1080 Ti11 GBgpuRuns~65 tok/s
NVIDIA GeForce RTX 2080 Ti11 GBgpuRuns~82 tok/s
Intel Arc B57010 GBgpuRuns~51 tok/s
NVIDIA GeForce RTX 3080 10GB10 GBgpuRuns~101 tok/s
AMD Radeon RX 6600 XT8 GBgpuRuns (tight)~34 tok/s
AMD Radeon RX 76008 GBgpuRuns (tight)~38 tok/s
Intel Arc A7508 GBgpuRuns (tight)~68 tok/s
AMD Radeon RX 9060 XT 8GB8 GBgpuRuns (tight)~36 tok/s
NVIDIA GeForce GTX 10708 GBgpuRuns (tight)~34 tok/s
NVIDIA GeForce RTX 2060 Super8 GBgpuRuns (tight)~60 tok/s
NVIDIA GeForce RTX 2070 Super8 GBgpuRuns (tight)~60 tok/s
NVIDIA GeForce RTX 2080 Super8 GBgpuRuns (tight)~66 tok/s
NVIDIA GeForce RTX 30508 GBgpuRuns (tight)~30 tok/s
NVIDIA GeForce RTX 3060 Ti8 GBgpuRuns (tight)~60 tok/s
NVIDIA GeForce RTX 30708 GBgpuRuns (tight)~60 tok/s
NVIDIA GeForce RTX 40608 GBgpuRuns (tight)~36 tok/s
NVIDIA GeForce RTX 4060 Ti 8GB8 GBgpuRuns (tight)~38 tok/s
NVIDIA GeForce RTX 50508 GBgpuRuns (tight)~30 tok/s
NVIDIA GeForce RTX 5060 Ti 8GB8 GBgpuRuns (tight)~60 tok/s
NVIDIA GeForce RTX 50608 GBgpuRuns (tight)~45 tok/s
MacBook Air M1 8GB8 GBmacRuns (tight)~9 tok/s
MacBook Air M2 8GB8 GBmacRuns (tight)~13 tok/s
NVIDIA GeForce GTX 1660 Super6 GBgpuCPU Offload~14 tok/s
NVIDIA GeForce RTX 20606 GBgpuCPU Offload~14 tok/s