Difference between revisions of "IT-AI-Ollama"
Jump to navigation
Jump to search
Samerhijazi (talk | contribs) (Created page with "=Settings= <pre class="code"> export OLLAMA_FLASH_ATTENTION=true export OLLAMA_KV_CACHE_TYPE=q8_0 ### f16 (for 7B–13B), q8_0 (for 34B, 70B) export OLLAMA_CONTEXT_LENGTH=3276...") |
Samerhijazi (talk | contribs) (→API) |
||
| (3 intermediate revisions by the same user not shown) | |||
| Line 8: | Line 8: | ||
export OLLAMA_NUM_THREAD=10 | export OLLAMA_NUM_THREAD=10 | ||
export OLLAMA_ORIGINS="*" | export OLLAMA_ORIGINS="*" | ||
| + | export OLLAMA_HOST="127.0.0.1:11434" | ||
</pre> | </pre> | ||
| + | =Commands= | ||
<pre class="code"> | <pre class="code"> | ||
| + | ollama serve ### Starts the Ollama background server (default: http://localhost:11434) | ||
| + | ollama launch ### Launch the Ollama menu | ||
| + | ollama run <model> ### Starts an interactive chat session with a model. | ||
| + | ollama run gemma4 "what is a black hole" | ||
| + | -------------------------------------------------------------------------------------- | ||
| + | ollama launch claude --model qwen3.6 | ||
| + | ollama launch opencode --model qwen3.6 | ||
| + | -------------------------------------------------------------------------------------- | ||
ollama run gemma4:31b "what is a black hole" | ollama run gemma4:31b "what is a black hole" | ||
ollama run deepseek-coder-v2:16b "what is a black hole" | ollama run deepseek-coder-v2:16b "what is a black hole" | ||
ollama run qwen3-coder:30b-a3b-q4_K_M "what is a black hole" | ollama run qwen3-coder:30b-a3b-q4_K_M "what is a black hole" | ||
| + | </pre> | ||
| + | =API= | ||
| + | <pre class="code"> | ||
| + | http://localhost:11434/api/tags | ||
| + | http://localhost:11434/api/show | ||
| + | http://localhost:11434/api/ps | ||
</pre> | </pre> | ||
Latest revision as of 00:26, 31 May 2026
Settings
export OLLAMA_FLASH_ATTENTION=true export OLLAMA_KV_CACHE_TYPE=q8_0 ### f16 (for 7B–13B), q8_0 (for 34B, 70B) export OLLAMA_CONTEXT_LENGTH=32768 ### 65536 for large codebase work export OLLAMA_NUM_PARALLEL=1 export OLLAMA_MAX_LOADED_MODELS=1 export OLLAMA_NUM_THREAD=10 export OLLAMA_ORIGINS="*" export OLLAMA_HOST="127.0.0.1:11434"
Commands
ollama serve ### Starts the Ollama background server (default: http://localhost:11434) ollama launch ### Launch the Ollama menu ollama run <model> ### Starts an interactive chat session with a model. ollama run gemma4 "what is a black hole" -------------------------------------------------------------------------------------- ollama launch claude --model qwen3.6 ollama launch opencode --model qwen3.6 -------------------------------------------------------------------------------------- ollama run gemma4:31b "what is a black hole" ollama run deepseek-coder-v2:16b "what is a black hole" ollama run qwen3-coder:30b-a3b-q4_K_M "what is a black hole"
API
http://localhost:11434/api/tags http://localhost:11434/api/show http://localhost:11434/api/ps
