
VRAMGlass
What LLM Can I Run
RunMyLLM
SelfHostLLM
slopsome.com
Free LLM VRAM calculator: estimate GPU memory for local LLMs (weights, KV cache, overhead), checked against 19 public llama.cpp/vLLM logs with a 1.2% median error.

RunMyLLM
slopsome.com
QWQ-Max
Ollama
VRAMGlass
Mistral 7B
AgentGPT
Hardware-aware AI model discovery. Enter your GPU and VRAM — instantly see every LLM that fits, ranked by speed and quality.

Which is more popular?
Website, pricing, platforms and company facts side by side.
|
|
|
|
|---|---|---|
| Website | modelvram.com | runyard.dev |
| Pricing | ||
| Company | — | Startup from India · 1 - 9 employees · 2026 |
| Listed in |
In their own words, as submitted to SaaSHub.


ModelVRAM is a free GPU memory calculator for running and fine-tuning LLMs locally. Pick a model from Hugging Face, a quantization and a context length, and it splits the total into weights, KV cache and runtime overhead, then lists the GPUs and Macs that fit. Every page includes a ready-to-run...
Runyard helps you discover AI models that fit your machine. It detects your CPU, GPU, and memory, then recommends models that will run on your hardware or through providers. Browse the Model Radar to compare options, check requirements, and copy ready-to-run commands. Use Anchor API to call...
What each product offers, as listed by its team.


No features have been listed yet.
An editorial look at what each product does well and who it suits.


No analysis of ModelVRAM yet.
Overall verdict
Why this product is good
Recommended for
How often each product is chosen within a category, 0–100% relative to the other.


As answered by people managing ModelVRAM and Runyard.dev.
Runyard.dev's answer:
Runyard.dev is the only tool that matches local LLMs to your exact hardware GPU, VRAM and RAM so you know which models will actually run on your machine before you download anything. No guesswork, no trial and error.
Runyard.dev's answer:
Developers, researchers, and AI enthusiasts who want to run LLMs locally but don't want to waste time figuring out compatibility. Anyone who's ever downloaded a model only to find it doesn't fit in their VRAM.
Share your experience with using ModelVRAM and Runyard.dev. For example, how are they different and which one is better?
When comparing ModelVRAM and Runyard.dev, you can also consider the following products.

Find the right GPU for local LLMs. Compare VRAM, GPU prices and model memory requirements to choose hardware that fits your models and budget.
Compare VRAMGlass to ModelVRAM or Runyard.dev:
Pick your GPU or Apple Silicon chip and see which open-weight LLMs fit — with a recommended model per job (coding, reasoning, vision, agents, speed), quantised weight sizes, KV cache at your context length, estimated tokens per second.
Compare RunMyLLM to ModelVRAM or Runyard.dev:

Hardware-first ranking of local LLMs. Tell us your machine, get every model that fits — ranked by real benchmarks (LiveBench, Aider, Arena), with the math shown.
Compare What LLM Can I Run to ModelVRAM or Runyard.dev:

Search engine for LLM & GPU stats — compare local open-weight and API models and the GPUs that run them. See what fits your rig, how fast, and at what cost. Community reviews, real tokens/sec and a live VRAM fit-calculator.
Compare slopsome.com to ModelVRAM or Runyard.dev:

Calculate the GPU memory you need for LLM inference
Compare SelfHostLLM to ModelVRAM or Runyard.dev: