LLM AI Server with llama.cpp

Alle versies van LLM AI Server with llama.cpp

• 
  2026.11.01.0054(29891574)Dit is de nieuwste versieLatest

  XAPK

  Nov 7, 20268.4 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.11.01.0054

  Bijgewerkt op Nov 7, 2026

  
  • Updated to the latest llama.cpp version with support for LFM3 models.
  • Added parallel loading support for embedding models and LLMs.
  

• 
  2026.10.26.1301(29883661)

  XAPK

  Oct 26, 20267.9 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.10.26.1301

  Bijgewerkt op Oct 26, 2026

  • Swagger UI at /swagger. Anthropic & Gemini API enhancements.
  • New endpoints: /api/ps, /api/show, /api/delete, /lora-adapters.
  • LLM AI Server Guide profile and connection check panel.
  • LoRA adapters, GGUF Generator link for model creation.
  • Added configurable CORS support for browser-based AI applications.
  • Improved model selection for Direct Run. Fixed MTP and other issues.

• 
  2026.10.19.1251(29873571)

  XAPK

  Oct 21, 20267.9 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.10.19.1251

  Bijgewerkt op Oct 21, 2026

  • Swagger UI at /swagger. Anthropic & Gemini API enhancements.
  • New endpoints: /api/ps, /api/show, /api/delete, /lora-adapters.
  • LLM AI Server Guide profile and connection check panel.
  • LoRA adapters, GGUF Generator link for model creation.
  • Improved model selection for Direct Run. Fixed MTP and other issues.

• 
  2026.10.15.0947(29867627)

  XAPK

  Oct 16, 20267.9 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.10.15.0947

  Bijgewerkt op Oct 16, 2026

  • Swagger UI at /swagger. Anthropic & Gemini API enhancements.
  • New endpoints: /api/ps, /api/show, /api/delete, /lora-adapters.
  • LLM AI Server Guide profile and connection check panel.
  • LoRA adapters, GGUF Generator link for model creation, Qwen3-VL default vision, llama.cpp b10621.

• 
  2026.10.13.0057(29864217)

  XAPK

  Oct 14, 20267.9 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.10.13.0057

  Bijgewerkt op Oct 14, 2026

  • Swagger UI at /swagger. Anthropic & Gemini API enhancements.
  • New endpoints: /api/ps, /api/show, /api/delete, /lora-adapters.
  • LLM AI Server Guide profile and connection check panel.
  • LoRA adapters, Qwen3-VL default vision, llama.cpp b10621.

• 
  2026.09.23.0954(29835954)

  XAPK

  Sep 23, 20267.6 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 2026.09.23.0954

  Bijgewerkt op Sep 23, 2026

  • LoRA adapters: apply LoRA GGUF at runtime; manage adapters in Settings.
  • Gemini API: Google‑compatible endpoints — /v1beta/models/:generateContent and :streamGenerateContent (v1 alias included).
  • MCP integration: resolved handshake failures and stabilized tool registration across sessions.

• 
  1.620(620)

  XAPK

  Sep 6, 20267.6 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 1.620

  Bijgewerkt op Sep 6, 2026

  • Vision: Qwen3‑VL now default; GPU→CPU fallback; improved model search + one‑tap mmproj.
  • n_ctx auto‑expands; over‑limit inputs return a clean server error.
  • Engine: llama.cpp b10621 / ggml 0.22 with broader model/GPU support.
  • Defaults: Chat = Qwen3.5‑2B, Vision = Qwen3‑VL.
  • Fixes: missing BOS; streaming continues.

• 
  1.590(590)

  XAPK

  Aug 31, 20267.3 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 1.590

  Bijgewerkt op Aug 31, 2026

  - New: OpenAI /v1/completions + Anthropic Messages API, improved WebUI streaming
  - API server keeps running during screen-off / low-power state, with auto-restart and preserved state
  - Fixed shutdown-related issues; more stable large-model loading (mmap), clearer crash messages, new profiles: default / Chat / Vision

• 
  1.580(580)

  XAPK

  Aug 12, 20267.2 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 1.580

  Bijgewerkt op Aug 12, 2026

  KV Cache Quantization Enhancements
  Improved nPredict Handling
  Stronger App–WebUI Integration
  GPU Load Stability Improvements
  Tokenizer API Added
  General Quality & Performance Improvements
  Profile backup and restore

• 
  1.554(554)

  XAPK

  Jul 26, 20267.2 MBAndroid 7.0+Wat is er nieuw
  Download
  Wat is er nieuw in versie 1.554

  Bijgewerkt op Jul 26, 2026

  Some small issues have been fixed.
  MTP support
  Qwen Vision support
  UI improvements with multilingual support
  Various bug fixes.