nlpguy/Qwen3.8-27B-Fimi-4

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 24, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

The nlpguy/Qwen3.8-27B-Fimi-4 is a 27 billion parameter language model, merged from multiple Qwen-based models using the Reinforced Agent Merging Plus (Tensor-Local) method. Built upon the Qwen/Qwen3.5-27B base, this model integrates diverse capabilities from several specialized Qwen 3.6 and 3.8 variants. It is designed to combine the strengths of its constituent models, offering a versatile foundation for various natural language processing tasks.

Loading preview...

Model Overview

nlpguy/Qwen3.8-27B-Fimi-4 is a 27 billion parameter language model created through a sophisticated merging process. It leverages the Reinforced Agent Merging Plus (Tensor-Local) method, using Qwen/Qwen3.5-27B as its foundational base model. This approach combines the strengths of several pre-trained Qwen-based models, aiming to produce a more robust and versatile language model.

Merge Details

The model integrates contributions from a diverse set of Qwen 3.6 and 3.8 variants, including:

  • Danielbrdz/Barcenas-Qwen3.8-27B-Fable
  • beyoru/Kiwen1.1-27B
  • empero-ai/Qwythos-27B-v1
  • bottlecapai/ThinkingCap-Qwen3.6-27B
  • TeichAI/Qwen3.8-27B-Fable-Distill
  • allenai/tmax-27b
  • migtissera/Tess-4-27B

This merging strategy allows the model to inherit and blend the specific characteristics and optimizations present in each of its constituent models. The configuration specifies a bfloat16 data type and utilizes a qwen chat template, indicating its compatibility with the Qwen ecosystem.

Potential Use Cases

Given its merged nature from various specialized Qwen models, nlpguy/Qwen3.8-27B-Fimi-4 is likely suitable for a broad range of applications where a general-purpose, high-capacity language model is beneficial. Developers seeking a model that combines different strengths from the Qwen family may find this merge particularly useful for tasks requiring nuanced understanding and generation.