whereismyai
RunThisLLM
RunThisLLM is a web-based database that identifies necessary hardware specifications for running specific local AI models and images.
Run This LLM allows users to look up hardware requirements for various local AI models. The database covers over 295 models, including Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, FLUX, and Whisper. Users can search by hardware they currently own to see what models they can run, or search by a specific model to see required hardware specifications. The tool provides full build specs, VRAM requirements, performance estimates, and benchmark scores. It also offers a custom build service where users request a machine optimized for specific models and budgets. The service covers diverse categories including general chat, code generation, vision, and audio.
RunThisLLM at a glance
- Best for: Software engineer
- Runs on: Web, Chrome extension
- Pricing: Free
- Released: March 2026
- Category: AI coding tool
- Website: runthisllm.com
Key features
- Search database of 295+ AI models
- Display VRAM requirements and build specs
- Provide performance estimates and benchmarks
- Identify runnable models based on existing hardware
- Custom machine specification and build service
Use it for
- Determine hardware needed for specific LLMs
- Find AI models compatible with current hardware
- Request custom machine builds for local AI development
Alternatives to RunThisLLM
- llmrun — Check which open models run on your specific GPU or Mac instantly.
- Strata — Runs large AI models locally on consumer gaming PCs without server reliance.
- AirLLM — Runs massive 70B+ parameter models on small 4GB consumer GPUs.
- whichllm — Ranks models using real benchmarks and hardware fit instead of parameter count.
- Project Maya — Runs a 321B-parameter AI model locally across VRAM, RAM, and NVMe SSD.
- GPUStack — Unifies AI model serving and GPU compute management across heterogeneous hardware.
- Daytona — It provisions sandboxes in under 90 milliseconds with full security isolation.
- llm-d — Deploys production-grade LLM serving on existing hardware clusters.
- RunAnywhere — Runs frontier models on hosted infrastructure or local hardware.
- SmallCode — Runs fully local with budget-managed context and a forgiving parser for small models.
- Soup — Fine-tune and align models like Llama-3.1-8B on a 4 GB laptop GPU.
- BitRun — Runs 1-bit and 1.58-bit ternary models on commodity CPUs without compilation or heavy Docker images.
All RunThisLLM alternatives