Kanjdoes/MewoQwen3-1.7B

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 11, 2026Architecture:Transformer Featherless Exclusive Cold

Kanjdoes/MewoQwen3-1.7B is a 1.7 billion parameter language model, fine-tuned and converted to GGUF format using Unsloth. This experimental model is based on the Qwen3 architecture and is provided with various quantization options. It is primarily intended for exploration and deployment via tools like llama-cli or Ollama, with no specific practical use cases highlighted.

Loading preview...

Overview

Kanjdoes/MewoQwen3-1.7B is an experimental 1.7 billion parameter language model, fine-tuned and converted into GGUF format using the Unsloth framework. This model is provided with several quantization options, including Q2_K, Q3_K_S, Q3_K_M, Q3_K_L, Q4_K_M, and Q4_0.

Key Characteristics

  • Architecture: Based on the Qwen3 model family.
  • Parameter Count: 1.7 billion parameters.
  • Format: Available in GGUF format, suitable for local inference engines.
  • Optimization: Fine-tuned with Unsloth, enabling faster training.
  • Deployment: Includes an Ollama Modelfile for simplified deployment.

Intended Use

This model is presented as an experiment with no specific practical use cases identified by the developer. It is primarily for users interested in exploring models fine-tuned with Unsloth and deploying them via llama-cli or Ollama. Users should note its experimental nature and lack of defined applications.

Finetunes
1 models