AI BriefingTiel-Coder-35B-A3B-GGUF: Coding-specialized LLM delivering 3B-class speed with 35B parameters
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF
About the project
This is a coding-specialized model based on Ornith-1.5-35B-A3B. Although it has a total of 35B parameters, thanks to its MoE architecture, only 3B parameters are activated during actual inference, providing lightweight speed.
Inference intensity can be finely adjusted according to control tags included in the prompt. Step-by-step settings are available from 'low' to 'xhigh', and the conciseness and logical depth of responses are automatically adjusted to match each mode.
By default, 'terse' mode is applied, which removes verbose greetings and unnecessary explanations to deliver only the core points. It maintains accuracy even in complex tool calls and multi-step agent tasks while reducing unnecessary token waste.
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF
The original page has no description.
image-text-to-text
This introduction was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report errors, attribution issues, or removal requests via Contact.