527 2 weeks ago

Trained for hermes agent

tools thinking
ollama run gurubot/Carnice-27b-GGUF:Q4_K_M

Applications

Claude Code
Claude Code ollama launch claude --model gurubot/Carnice-27b-GGUF:Q4_K_M
OpenClaw
OpenClaw ollama launch openclaw --model gurubot/Carnice-27b-GGUF:Q4_K_M
Hermes Agent
Hermes Agent ollama launch hermes --model gurubot/Carnice-27b-GGUF:Q4_K_M
Codex
Codex ollama launch codex --model gurubot/Carnice-27b-GGUF:Q4_K_M
OpenCode
OpenCode ollama launch opencode --model gurubot/Carnice-27b-GGUF:Q4_K_M

Models

View all →

Readme

image.png

Carnice-27b is the merged full-model release of the Trinity Hermes-Agent training run on top of Qwen/Qwen3.5-27B.

Trained using traces from lambda/hermes-agent-reasoning-traces

Carnice-27b is tuned for Hermes-Agent style terminal, file, browser, repo, debugging, and multi-step tool workflows.

source https://huggingface.co/kai-os/Carnice-27b