# VRAMFit: LLM Calculator — Will that LLM fit your GPU? > Calculates LLM VRAM requirements for local GPU and Apple Silicon hardware. (iPhone/iPad app by Sarvesh Anand Kandala.) - Source: https://appshunter.io/ios/app/vramfit-llm-calculator/id6789931132 (this page in markdown: same URL + `.md`) - Developer: [Sarvesh Anand Kandala](https://appshunter.io/developer/6789931134) - Category: Developer Tools, Utilities - Price: Free - Rating: 5.00/5 from 1 App Store ratings - Age rating: 4+ - Requires: iOS 18.0 · 1 MB - Languages: American English - Released: 2026-07-21 - Data updated: 2026-09-07 - Monetization: freemium - User reviews in markdown: https://appshunter.io/ios/app/vramfit-llm-calculator/id6789931132/reviews.md ## What is VRAMFit? Before you download gigabytes of model weights, know whether they'll actually fit. VRAMFit tells you the largest local large language model you can run on your hardware — whether that's an NVIDIA GPU's VRAM or the unified memory on an Apple Silicon Mac. Set your memory, pick a quantization, and get a clear, instant answer. Built for people who run models locally: llama.cpp, Ollama, LM Studio, and anyone deciding what GPU to buy next. MEASURED, NOT GUESSED Most calculators multiply a parameter count by a rule of thumb. VRAMFit ships the real size of the published file for every model at every quantization it is actually released in, and names the exact build each figure came from — so you can check it against the download before you start it. That matters most where rules of thumb break. A ternary model has no 4-bit build to estimate. A natively 4-bit model barely changes size as you move up the scale. VRAMFit says what those models actually weigh, or tells you plainly that the build you picked does not exist. WHAT IT DOES • Enter your VRAM (or Apple Silicon RAM) and instantly see what fits • Sorts the catalog into what runs, what runs one setting down, and what won't • Accounts for quantization — from full precision down to 4-bit and FP4 • Factors in context length and KV cache, the memory costs people usually forget • Switches between discrete GPU and Apple Silicon unified-memory math FREE • The full calculator, with quantization, context, and FP4 • A starter set of models spanning what fits and what nearly fits • GPU and Apple Silicon modes VRAMFit Pro (one-time upgrade) • The complete catalog of 73 current open models, measured • Per-quantization memory breakdown for every model • Advanced tools: KV-cache compression and multi-token prediction estimates PRIVATE BY DESIGN VRAMFit runs entirely on your device. No account, no sign-in, no tracking, and nothing about you leaves your iPhone. The numbers you enter stay with you. Stop guessing whether a model will fit. Check first, download once. ## Key features - Calculate LLM fit for GPU and Apple Silicon - Accounts for quantization (4-bit, FP4) - Includes context length and KV cache costs - Provides measured, not guessed, model sizes - Sorts models by what fits and what nearly fits ## Frequently asked questions about VRAMFit ### What is VRAMFit? VRAMFit is a developer tool that helps you determine the largest local large language model (LLM) that will fit into your computer's VRAM or unified memory. It provides measured sizes for models at various quantizations, factoring in context length and KV cache. ### How does VRAMFit calculate model sizes? Unlike other calculators that use rules of thumb, VRAMFit uses the actual file size of published models at specific quantizations. This ensures accuracy, especially for models with unique characteristics like ternary or natively 4-bit builds. ### What hardware does VRAMFit support? VRAMFit supports both NVIDIA GPUs for VRAM calculations and Apple Silicon Macs for unified memory calculations. You can switch between these modes within the app. ### Does VRAMFit have ads? No, VRAMFit is ad-free. The free version offers the full calculator functionality, and an optional one-time upgrade to VRAMFit Pro unlocks the complete model catalog and advanced tools. ### Is VRAMFit private? Yes, VRAMFit is designed to be private. It runs entirely on your device, requiring no account, sign-in, or tracking. Your entered data stays with you. ### What is the difference between VRAMFit and VRAMFit Pro? The free version of VRAMFit includes the full calculator with quantization, context, and FP4 support, along with a starter set of models. VRAMFit Pro, a one-time upgrade, provides the complete catalog of 73 current open models, per-quantization breakdowns, and advanced tools like KV-cache compression estimates. ### How often is VRAMFit updated? The latest version of VRAMFit is 1.1.0, last updated on September 3, 2026. Updates typically include new model data and feature enhancements. ### What is the age rating for VRAMFit? VRAMFit has an age rating of 4+, making it suitable for a wide range of users interested in LLM hardware compatibility. ## Version history (last 2 releases) ### 1.1.0 — 2026-09-03 Model sizes are now measured, not calculated. VRAMFit used to size a model by multiplying its parameters by a rule of thumb for each quantization. It now ships the real size of the published file for every model at every setting it is actually released in, and names the exact build each number came from. • A much larger catalog of current open models, every one measured • Models that only exist at one quantization say so, instead of showing a size for a build that was never published • Natively 4-bit models no longer appear to grow as you move up the scale • The list is grouped into what fits, what fits one setting down, and what won't — so a model that just misses tells you which setting would run it • Rewritten help explaining where the numbers come from and what they still cannot know Estimates are higher than before at every setting. That is the correction: the old rule of thumb ran low. ### 1.0 — 2026-07-21 No release notes. ## More apps by Sarvesh Anand Kandala - [Felicity: AI Concierge](https://appshunter.io/ios/app/felicity-ai-concierge/id6794885199) All apps by Sarvesh Anand Kandala: https://appshunter.io/developer/6789931134 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-09-07.*