froggeric / Qwen3.6-27B-MTP-GGUF

Vision2.7K81Updated May 21, 2026

Downloads

2.7K

Likes

81

Last updated

May 21, 2026

License

apache-2.0

Dense 27B model with vision, thinking, and tool use — self-speculative decoding, \ configurable KV cache, fixed Jinja template (tool calls and thinking actually work in C++ runtimes), \ and a server with both OpenAI and Anthropic APIs.

Tasks & library

  • image text to text
  • llama.cpp

Tags

  • llama.cpp
  • gguf
  • qwen3.6
  • qwen3_5
  • conversational
  • vision

Technical specifications

ParametersNot available
Libraryllama.cpp
Languagesen, zh, multilingual
Licenseapache-2.0