simbolmina/voxpage-8k-v2

VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:5.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:May 7, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

The simbolmina/voxpage-8k-v2 is a 5.1 billion parameter language model, fine-tuned and converted to GGUF format using Unsloth. This model is designed for both text-only and multimodal applications, supporting a context length of 32768 tokens. Its primary distinction lies in its multimodal capabilities, offering specific configurations for vision models, and its efficient training process via Unsloth.

Loading preview...

Model Overview

The simbolmina/voxpage-8k-v2 is a 5.1 billion parameter model, fine-tuned and converted into the GGUF format using the Unsloth framework. It supports a substantial context length of 32768 tokens, making it suitable for processing longer sequences of text.

Key Capabilities

  • Text-only Generation: Can be used with standard llama-cli for text-based tasks.
  • Multimodal Support: Features specific GGUF files (BF16-mmproj.gguf) designed for multimodal applications, enabling processing of both text and visual inputs.
  • Efficient Training: Leverages Unsloth for faster fine-tuning, indicating potential for rapid adaptation to specific tasks.

Usage Notes

  • GGUF Format: Provided in various GGUF quantizations, including Q2_K_L and BF16-mmproj for multimodal use.
  • Ollama Compatibility: Special instructions are provided for creating Ollama-compatible models from the vision-enabled bf16 merged model, as Ollama currently does not support separate mmproj files. This involves placing a Modelfile alongside the merged model and using the ollama create command.

Finetunes
1 models