Poštovani,
od 01.01.2026 uvodimo novi cjenik, pa Vas molimo da provjerite nove cijene.

Poštovani korisnici dane 05.08.2026, 15.08.2026. te od 20 -24.08.2026. teretana ne radi i te dane treninzi se neće održati.

 

Deploy flux2-dev Full Speed NPU Mode Easy Build

🖹 HASH-SUM: 0f6b32af40271e2f0a18bd73e41637de | 📅 Updated on: 2026-07-15 Verify CPU: AVX2/AVX-512 instruction set required for llama.cpp RAM: required: 16 GB absolute minimum for small models Disk Space:70 GB free space for full FP16 weights storage GPU: 16 GB+ video memory highly recommended for exl2 / AWQ formats Achieving Groundbreaking Performance in Text-to-Image Generation The flux2-dev …

Pročitaj više

How to Install Qwen3-VL-8B-Instruct For Beginners

🛡️ Checksum: df4658cd65236fb9436cdc371972cfc5 — ⏰ Updated on: 2026-07-19 Verify CPU: multi-threading optimized for fast prompt processing RAM: 32 GB highly recommended for 26B+ GGUF models Storage:100 GB free space for HuggingFace cache folder Graphics: 12 GB VRAM minimum required for basic quantization Diving into the Depths of Qwen3-VL-8B-Instruct The Qwen3-VL-8B-Instruct model is an extraordinary vision-language …

Pročitaj više

How to Setup Kimi-K2.5-NVFP4 5-Minute Setup

💾 File hash: 4e9227ac9dfdc8b0b2ad0b5e391e1b6f (Update date: 2026-07-14) Verify CPU: modern architecture (Zen 3 / Alder Lake minimum) RAM: minimum 16 GB for stable 8B model loading Disk Space: free: 80 GB on system drive for scratch space Graphics: TensorRT-LLM / vLLM inference engine compatible chip The Breakthrough in Efficient Inference for Large Language Tasks The …

Pročitaj više

How to Deploy ESMC-6B Locally via Ollama 2 No-Internet Version Complete Walkthrough

🔍 Hash-sum: 7cb158d7206901e496a0abf7950749f2 | 🕓 Last update: 2026-07-12 Verify CPU: 8-core / 16-thread recommended for orchestration RAM: fast 5600MHz+ required to avoid memory bottlenecks Disk Space:70 GB free space for full FP16 weights storage Graphics: stable 30+ tk/s at 4-bit quantization on medium setup Detailed Features and Capabilities of ESMC-6B The ESMC-6B parameter language model …

Pročitaj više

Quick Run Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive via WebGPU (Browser) Easy Build

🧾 Hash-sum — 1595fcdc7181b5952a5c21e724c9e11e • 🗓 Updated on: 2026-07-17 Verify CPU: 8-core / 16-thread recommended for orchestration RAM: 48 GB needed to prevent memory swapping to disk Storage: extra room for future model updates and datasets GPU: modern architecture (Ada Lovelace / Ampere minimum) The Unbridled Genius of Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive The Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive is a behemoth of …

Pročitaj više

Qwen3.5-4B-GGUF on Copilot+ PC Full Speed NPU Mode

📘 Build Hash: d0e353bd2bf42fbac2c032459f63946f • 🗓 2026-07-17 Verify Processor: high single-core performance needed for token latency RAM: high-speed DDR5 memory preferred for CPU offloading Disk: high-speed SSD 120 GB to cache model layers Graphics: TensorRT-LLM / vLLM inference engine compatible chip The Qwen3.5-4B-GGUF Model: A Powerhouse for Natural Language Tasks The Qwen3.5-4B-GGUF model is a …

Pročitaj više

How to Install OmniVoice Zero Config Offline Setup Windows

🛠 Hash code: fdbbf99d52aa118e9c8b36fe46bbb285 — Last modification: 2026-07-15 Verify CPU: multi-threading optimized for fast prompt processing RAM: 48 GB needed to prevent memory swapping to disk Storage:100 GB free space for HuggingFace cache folder Graphics: CUDA Compute Capability 8.0+ required for flash-attention Unlocking the Potential of Human-AI Collaboration The advent of OmniVoice marks a significant …

Pročitaj više