Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Open source
24 alternativesWhichLLM
WhichLLM tests local language models on a user’s hardware and ranks them using recent benchmarks.
About WhichLLM
WhichLLM checks a computer's GPU, CPU and RAM and lists HuggingFace language models that fit, ordered by merged benchmark results including LiveBench, Artificial Analysis, Aider and Chatbot Arena ELO. The default table shows memory use, estimated generation speed, fit type and publication date.
It can run once with uvx without project setup, or be installed with uv, brew or pip. By default it includes partial RAM offload and near-edge VRAM fits; options limit results to full GPU fit, filter by speed, simulate other GPUs, and produce markdown, JSON or Python snippets.
Key features
- Auto-detects GPU, CPU and RAM to filter runnable models
- Ranks HuggingFace models using merged benchmark scores
- Simulates named GPUs, including multi-GPU workstations
- Filters for full GPU-VRAM fit and speed thresholds
- Compares GPUs and estimates hardware needed for models
- Outputs markdown, JSON, Python snippets; can start chat
Best for: People choosing a local language model to run on existing or planned hardware.
Good for
- Ranks by benchmark scores and recency rather than parameter count alone
- Runs once with no project setup
- Shows fit type and speed usability with estimate confidence marks
Watch out for
- Default list can include partial offloads and tight VRAM fits
- Speed figures are estimates, marked with ~ or ? for confidence
WhichLLM at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
WhichLLM alternatives
Tools and sites you could use instead, ranked by how closely they match.
LLMeBench provides a flexible framework for benchmarking large language models.
AwaDB provides an AI-focused embedding vector database with real-time search features.
Open source
24 alternatives
Aider LLM Leaderboards compares language models on code editing benchmarks.
skill-optimizer benchmarks, evaluates, and optimizes skills to check their performance across large language models.
Open source
24 alternatives
Turbostream analyzes real time streaming data with large language models.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
WhichLLM FAQ
Do I need to install WhichLLM to use it?
No. You can run uvx whichllm@latest once with no project setup. Installation with uv tool, brew, or pip is for frequent use.
How can I get a more conservative recommendation?
Use --gpu-only --speed usable --vram-headroom 1GB to keep only models that fit fully in GPU VRAM, filter slow estimates, and leave overhead. Increase headroom to 1.5GB if needed.
Can I check models for hardware I do not have?
Yes. Use --gpu with a card name such as "RTX 4090", including multi-GPU values like "2x RTX 4090", to simulate that setup.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.