Ollama Library Models

Browse available models and pull them directly into your VPS Ollama instance.

Home Ollama Library

RAM Usage

43.5%

5.07 GB used / 11.65 GB total — 6.58 GB available

Disk Usage

49.7%

22.35 GB used / 44.96 GB total — 22.6 GB free

Browse Library

Search Ollama library models and install them into your server.

Installed Models

Manual Pull

Paste exact model string here, for example: llama3.2:3b or deepseek-r1:7b


Reset

Total lightweight library models found: 9

Library

qwen2.5

Qwen family with multiple small and medium variants.
Small variants (≤ 8b)
0.5b 1.5b 3b 7b
Run command
ollama run qwen2.5
View Details
Library

llama3.2

Lightweight Llama 3.2 series suitable for smaller systems.
Small variants (≤ 8b)
1b 3b
Run command
ollama run llama3.2
View Details
Library

deepseek-coder

DeepSeek coding model family for code generation tasks.
Small variants (≤ 8b)
1.3b 6.7b
Run command
ollama run deepseek-coder
View Details
Library

deepseek-r1

DeepSeek reasoning model family available in multiple sizes.
Small variants (≤ 8b)
1.5b 7b 8b
Run command
ollama run deepseek-r1
View Details
Library

granite4.1

Granite family with multiple parameter sizes.
Small variants (≤ 8b)
1.5b 7b
Run command
ollama run granite4.1
View Details
Installed

gemma2

Google Gemma 2 open models for local use.
Small variants (≤ 8b)
2b
Run command
ollama run gemma2
View Details
Library

phi3

Microsoft Phi series compact models.
Small variants (≤ 8b)
3.8b
Run command
ollama run phi3
View Details
Library

mistral

Mistral open-weight instruction models.
Small variants (≤ 8b)
7b
Run command
ollama run mistral
View Details
Library

llama3.1

Meta's Llama 3.1 family with multiple parameter sizes.
Small variants (≤ 8b)
8b
Run command
ollama run llama3.1
View Details