VRAM Fit

Work out, before you download, whether a model will actually fit on your GPU.

This site is deliberately narrow. Instead of covering a broad topic shallowly, every page here exists to answer one specific question properly — because a page that genuinely solves a problem is the only kind that keeps ranking, and the only kind worth reading.

Pages on this site

• VRAM Calculator: Will This Model Fit Your GPU?

  A working calculator for LLM VRAM: enter parameters, quant bits, layers, KV heads, head dim, and context to see weight + KV cache + headroom totals.

• KV Cache Size Explained: The Formula Behind Context Length

  Why long context eats VRAM: the KV cache formula, how GQA shrinks it, and a worked table showing KV cache doubling when you double the context length.

• GGUF Quantization Compared: What Q4_K_M Actually Costs You

  GGUF quant tiers Q2_K to F16: bits per parameter and the 7B, 13B, and 70B weight sizes, plus the quality-versus-memory tradeoff.

• Can You Actually Run a 70B Model Locally?

  A feasibility matrix for running a 70B LLM locally across GGUF quant tiers and common GPUs, including multi-GPU and CPU-offload outcomes.

• Ollama Out of Memory: What Actually Frees VRAM

  Ollama out-of-memory fixes that work: the real causes, what num_gpu and num_ctx do, and a symptom-to-root-cause table you can act on.

• llama.cpp GPU Offload Layers (-ngl) Explained

  What llama.cpp -ngl does: how many layers to offload to your GPU, the speed and memory tradeoff from -ngl 0 to all layers, and copy-paste command examples.

• Apple Silicon Unified Memory for LLMs: How Much Do You Need?

  How Apple Silicon unified memory fits LLMs: a tier-to-max-model table, why macOS reserves part of the pool, and how much you can really give a model.

• GPU VRAM Reference: What Each Card Actually Gives You

  A VRAM reference for local LLMs: nominal memory of common NVIDIA, AMD, and Apple cards, plus why usable VRAM is always less than the spec sheet says.

• MoE Models and VRAM: Total vs Active Parameters

  Why MoE VRAM depends on total parameters, not active ones, and how that differs from a dense model of the same size when fitting locally.

• Context Length Costs VRAM: Sizing a Real Session

  How context length drives KV cache VRAM: a chat-length to KV-cache table plus how batching and concurrency multiply memory on top of the model weights.

• How to Measure Real VRAM Usage While Running a Model

  Three commands to measure actual VRAM while a model runs on NVIDIA, macOS, and Linux, plus a table decoding what each reading means for your fit decision.

• LLM VRAM Math Cheatsheet

  Every VRAM formula for local LLMs on one page: weight size, KV cache, engine overhead, batch multipliers, and worked conversions you can do by hand.

• Privacy Policy

  What VRAM Fit collects, how Google AdSense and analytics use cookies, data retention, your rights, and how to contact us about privacy.

• About VRAM Fit

  What VRAM Fit is, why it exists, how its content is produced and checked, who operates it, and how to report an error.

• Contact VRAM Fit

  How to reach VRAM Fit by email, what we reply to and what we do not, expected reply time, and what this site is not.

• Terms of Service

  The terms governing use of VRAM Fit: content is reference only, intellectual property, third-party links, liability limits, and how terms change.

How this site is maintained

Pages are reviewed and updated on a rolling basis. When something changes — a number, a step, a recommendation — the existing page is corrected rather than duplicated, so what you are reading is the current version. If you spot an error, the contact page reaches a human.