Llamaport
Run local GGUF models with llama-server. Reads model headers directly for real quantisation and context length, shows the full launch command before starting, reports live token rates and memory pressure, and downloads models from Hugging Face with resume that survives a kill…
- from
- Open Source Apps
- added
- 2026-10-19
- likes
- 0
similar
-
Quail quail-ai.app
Local model server for GGUF and MLX models on Apple silicon, with OpenAI- and Anthropic-compatible APIs for tools like Claude Code and Codex.
-
LocalLLM github.com
Query local LLM models with Ollama.
-
Ollama github.com
Get up and running with large language models locally.
-
AlexsJones/llmserve github.com
[llmserve] - Interactive TUI to serve local LLM models with auto-detected backends (llama-server, KoboldCpp, LocalAI, MLX, Ollama, vLLM, LM Studio). Features source tree navigation, per-backend presets, live logs, and vision model support.
-
Llama llama.com
Meta's open source large language model. #opensource
-
Ollama github.com
Run large language models locally.
Open Source Apps › Applications > 👨💻 Development (38): “Run local GGUF models with llama-server. Reads model headers directly for real quantisation and context length, shows the full launch command before starting, reports live token rates and memory pressure, and downloads models from Hugging Face with resume that survives a kill…”