Featherless
Qwen3-4b-tcomanr-merge-v2.7Ertghiu256
Start Chat
4B Params BF16 Inference Available

The ertghiu256/Qwen3-4b-tcomanr-merge-v2.7 is a 4 billion parameter language model based on the Qwen3 architecture, created by ertghiu256 through a TIES merge of multiple specialized Qwen3-based models. This merge integrates capabilities from models focused on math reasoning, code reasoning, mixture-of-thought, and general instruction following. It is designed to offer enhanced performance across various reasoning and instruction-following tasks by combining diverse strengths.

Loading preview...

Parameters:4BContext length:32kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:December 2025
0.0M
0.0K

Model tree for

ertghiu256/Qwen3-4b-tcomanr-merge-v2.7
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

–

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

–

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

–

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

–

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

–

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

–

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.

–