最終更新:2025-08-06 (水) 17:31:13 (196d)
Ollama/モデル
Ollama/Modelfile
ollama run
Model Parameters Size Download Qwen3-30B-A3B 30B 19GB ollama run qwen3:30b Q4_K_M Qwen3-32B 32B 20GB ollama run qwen3:32b Q4_K_M Qwen3-14B 14B 9.3GB ollama run qwen3:14b Q4_K_M Qwen3-8B 8B 5.2GB ollama run qwen3 Q4_K_M Qwen3-4B 4B 2.6GB ollama run qwen3:4b Q4_K_M Qwen DeepSeek R1 1.5B 1.1GB ollama run deepseek-r1:1.5b Q4_K_M Qwen DeepSeek R1 (デフォルト) 7B 4.7GB ollama run deepseek-r1:7b Q4_K_M Llama DeepSeek R1 8B 4.9GB ollama run deepseek-r1:8b Q4_K_M Qwen DeepSeek R1 14B 9.0GB ollama run deepseek-r1:14b Q4_K_M Qwen DeepSeek R1 32B 20GB ollama run deepseek-r1:32b Q4_K_M Llama DeepSeek R1 70B 43GB ollama run deepseek-r1:70b Q4_K_M DeepSeek R1 671B 404GB ollama run deepseek-r1:671b Q4_K_M Llama 3.3 70B 43GB ollama run llama3.3 Phi-4 14B 9.1GB ollama run phi4 Q4_K_M QwQ 32B 20GB ollama run qwq Q4_K_M Llama 3.2 3B 2GB ollama run llama3.2 Q4_K_M Llama 3.2 1B 1.3GB ollama run llama3.2:1b Q8_0? Llama 3 8B 4.7GB ollama run llama3 Llama 3 70B? 70B 40GB ollama run llama3:70b Llama 2 7B 3.8GB ollama run llama2 Llama 2 13B 13B 7.3GB ollama run llama2:13b Llama 2 70B 70B 39GB ollama run llama2:70b Llama 2 Uncensored? 7B 3.8GB ollama run llama2-uncensored Mistral 7B 4.1GB ollama run mistral Dolphin Phi? 2.7B 1.6GB ollama run dolphin-phi Phi-2? 2.7B 1.7GB ollama run phi Neural Chat? 7B 4.1GB ollama run neural-chat Starling? 7B 4.1GB ollama run starling-lm Code Llama 7B 3.8GB ollama run codellama Orca Mini? 3B 1.9GB ollama run orca-mini Vicuna 7B 3.8GB ollama run vicuna LLaVA 7B 4.5GB ollama run llava Gemma 2 9B 5.4GB ollama run gemma2 Q4_0? Gemma 2 2B 1.6GB ollama run gemma2:2b Q4_0? Gemma 2B 1.4GB ollama run gemma:2b Gemma 7B 4.8GB ollama run gemma:7b DeepSeek-V3 671B 404GB ollama run deepseek-v3 Q4_K_M
モデルファイル
場所
Hugging Face Hub
- ollama run hf.co/{username}/{repository}
Elyza-7B?を試す
メモ
Ollama/モデル/llama2
- 7b models generally require at least 8GB of RAM
- 13b models generally require at least 16GB of RAM
- 70b models generally require at least 64GB of RAM
Ollama/モデル/llama2-uncensored
- 7b models generally require at least 8GB of RAM
- 70b models generally require at least 64GB of RAM
Ollama/モデル/gemma
- 2B
- 7B (デフォルト)
