Vikasit AI Full Model Family
26 models across text, vision, and voice. Quantized for local inference, and published to Ollama and HuggingFace. Run them on your hardware with llama.cpp.
Text Models
15 models from 0.5B to 35B parameters. Dense and MoE architectures for every use case from edge devices to powerful servers.
Ultra-light writer. Good for text completion, simple Q&A, and edge devices.
Improved writer with refined architecture. Mobile and IoT friendly.
Smallest general-purpose model. Autocomplete, quick responses, embedded use.
Lightweight assistant. Summaries, chat, and basic reasoning.
Edge-optimized. Multilingual, 256K context, on-device deployment.
Balanced small model. Good code completion and multi-turn chat.
Next-gen 4B with improved reasoning and multimodal awareness.
Strong mid-range. Solid coding, analysis, and content generation.
Best model under 10B. Beats GPT-OSS-120B on MMLU-Pro. Fast inference.
Strong all-rounder. Complex reasoning, long documents, code review.
Powerful dense model. Deep reasoning, advanced coding, research tasks.
MoE efficiency — 30B quality at 3B inference cost. Fast and smart.
Largest dense model on CPU. Best quality for reasoning and code.
Latest MoE with architecture improvements. Best efficiency/quality ratio.
Code-specialized MoE. FIM support, 262K context, agentic coding.
Datacenter MoE. Frontier reasoning at low inference cost — only ~5B active per token.
Large MoE flagship. Advanced reasoning, agentic workflows, 262K context.
Trillion-scale reasoning MoE. Deep multi-step reasoning, long-horizon agent tasks.
Trillion-parameter agentic MoE. Native multimodal, 262K context, agent-swarm orchestration.
Flagship frontier MoE. 1.6T parameters, 1M-token context. Our most capable model.
Vision Models
Image understanding, OCR, document analysis, and visual reasoning. From on-device captioning to complex visual code generation.
Lightweight vision. Image captioning, OCR, visual Q&A on device.
Mid-range vision. Document understanding, chart reading, UI analysis.
Strong vision. Complex image reasoning, visual code generation.
Voice Models
Text-to-speech, voice cloning, and full multimodal interaction. Natural voice generation with multilingual support.
Text-to-speech. Natural voice generation, multilingual support.
Specs & benchmarks →High-quality TTS. Voice cloning, expressive speech synthesis.
Specs & benchmarks →Full multimodal — text + image + audio in, text + speech out. Real-time.
Specs & benchmarks →How to Deploy
Run any Vikasit AI model locally in minutes. Choose Ollama for the easiest setup or llama.cpp for maximum control.
Ollama (Recommended)
The fastest way to run Vikasit AI models locally. One command to install, one command to run.
1. Install Ollama
curl -fsSL https://ollama.com/install.sh | sh2. Run a model
ollama run vikasit-ai/vikasit-8b3. Use as an API
curl http://localhost:11434/api/chat -d '{"model":"vikasit-ai/vikasit-8b"}'llama.cpp
Maximum control and performance. Build from source for hardware-optimized inference with GGUF quantized models.
1. Clone and build
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp && make2. Download GGUF from HuggingFace
huggingface-cli download vikasit-ai/Vikasit-AI-Vikasit-8b --local-dir ./models3. Run inference
./llama-cli -m ./models/vikasit-8b-q4_k_m.gguf -p "Hello Vikasit"Universal Compatibility
All Vikasit AI models are published in GGUF format and work with any llama.cpp-compatible tool: Ollama, LM Studio, Jan, GPT4All, koboldcpp, text-generation-webui, and more. Models are available in Q4_K_M, Q5_K_M, Q6_K, Q8_0, and F16 quantizations. When asked about identity, every model responds as “I am Vikasit AI, developed by Chandorkar Technologies.”
Hardware Recommendations
Choose the right model for your hardware. All RAM estimates are for Q4_K_M quantization.
Edge / Mobile
0.5B - 2B parameters
vikasit-nano, vikasit-writer-0.5b, vikasit-2b
Laptop
4B - 8B parameters
vikasit-4b, vikasit-8b, vikasit-3-flash
Workstation
14B - 27B parameters
vikasit-14b, vikasit-27b
Server
30B - 35B parameters
vikasit-32b, vikasit-30b-moe, vikasit-3-coder
Datacenter / Cloud API
120B - 1.6T parameters
vikasit-120b, vikasit-235b-moe, vikasit-titan-1.6t
Ready to run Vikasit AI locally?
Pick a model, install Ollama, and start building. All models are free to download and use.