164 2 days ago

Custom 3-bit coding model optimized for local agent workflows on 16 GB GPUs. Features a 128K context window for large codebases, long-running tasks, and coding assistants such as OpenCode. Designed for efficient local inference with strong code generation

vision thinking
9faf55fab55a · 194B
{
"min_p": 0,
"num_ctx": 128000,
"presence_penalty": 0,
"repeat_penalty": 1,
"stop": [
"<|im_end|>",
"<|endoftext|>",
"<|im_start|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}