Difference between revisions of "IT-AI-Ollama"

From wiki.samerhijazi.net
Jump to navigation Jump to search
(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...")
 
(Settings)
Line 9: Line 9:
 
export OLLAMA_ORIGINS="*"
 
export OLLAMA_ORIGINS="*"
 
</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>
 
</pre>

Revision as of 14:27, 7 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="*"

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"