
Runyard.dev
What LLM Can I Run
localLLMrig
ModelFit.cc
VRAMGlass
Hugging Face
SelfHostLLM
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.

CodeOcean
Bring literature, research ideas, reproducible workflows, and GPU and HPC compute into one workspace

Which is more popular?
Website, pricing, platforms and company facts side by side.
|
|
|
|
|---|---|---|
| Website | modelvram.com | constructor.tech |
| Pricing | ||
| Platforms | — | |
| 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...
Constructor Research gives academic and industrial research teams a shared workspace for exploring literature, developing research ideas, and running computational experiments. Hypothesis supports literature exploration and evidence-linked findings. Researchers can use ready-to-use GPU and...
What each product offers, as listed by its team.


Possible disadvantages
How often each product is chosen within a category, 0–100% relative to the other.


Share your experience with using ModelVRAM and Constructor Research. For example, how are they different and which one is better?
When comparing ModelVRAM and Constructor Research, you can also consider the following products.

Hardware-aware AI model discovery. Enter your GPU and VRAM — instantly see every LLM that fits, ranked by speed and quality.
Compare Runyard.dev to ModelVRAM or Constructor Research:

Code Ocean is a research collaboration platform. Create, collaborate on, share, execute, and publish computational code and data from anywhere, with anyone.
Compare CodeOcean to ModelVRAM or Constructor Research:

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 Constructor Research:

Test free open LLMs side by side in your browser, and check which GPU runs them.
Compare localLLMrig to ModelVRAM or Constructor Research:

Estimate LLM memory, test GPU fit, and turn a model into a practical deployment plan.
Compare ModelFit.cc to ModelVRAM or Constructor Research:

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 Constructor Research: