Developer Tools●●Solid
Ktop – a themed terminal monitor for GPU, CPU, RAM, temps and OOM kills
Monitors GPU+CPU+memory in one themed terminal view—leaner than Glances.
Solve My ProblemEye Candy
brontoguana
303mo ago
Back to browse
GitHub Repository
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
2,417 starsPython
Whichllm – Find and run the best local LLM for your hardware
by andyyyy64·Mar 9, 2026·3 points·0 comments
AI Analysis
●●●BangerSolve My ProblemBig BrainNiche Gem
One command finds and runs the best local LLM for your exact hardware specs.
Strengths
- •Live HuggingFace API data beats static model databases in competing tools.
- •JSON output and scriptable design enables CI/CD pipeline integration easily.
- •GPU simulation flag lets you test model fit before buying hardware.
Weaknesses
- •Local LLM tooling space is getting crowded with Ollama and LM Studio.
- •Model download still requires significant disk space regardless of detection.
Category
Target Audience
Developers running local LLMs
Similar To
Ollama · LM Studio · llama.cpp
Similar Projects
Finance●Mid
RAM Fear Greed Index
Fear-greed index for PC parts, but limited to Dutch pricing and 12-month history.
Solve My Problem
flordaman
202mo ago
AI/ML●●Solid
Llmfit;94 models, 30 providers.1 tool to see what runs on your hardware
The project nails a real pain: instead of guessing whether a 7B or 13B model will fit, llmfit inspects your system and ranks 94 models by fit, speed, context and quality, even recommending quantization and run modes and supporting multi‑GPU and MoE setups. The combo of an installable binary, interactive TUI for quick browsing and JSON output for automation makes it immediately useful; just remember its suggestions are heuristics — you’ll still want to validate edge cases with a real run.
Solve My ProblemWizardry
axjns
103mo ago
AI/ML●●Solid
Find the best local LLM for your hardware, ranked by benchmarks
Ranks models by actual benchmark scores instead of just fitting the biggest model in VRAM.
Solve My ProblemShip It
andyyyy64
2836820d ago
AI/ML●●Solid
AI/ML benchmark for local LLM inference and XGBoost training on GPU/CPU
One-command benchmark suite comparing Ollama and XGBoost performance with a shared Streamlit dashboard.
Solve My ProblemNiche Gem
albedan
2019d ago
AI/ML●●Solid
TubeTrim – A local YouTube summarizer using Qwen in pure Python
Local Qwen 2.5-1.5B summarization when Glasp and Eightify already exist.
CozySolve My Problem
guglielmoce
102mo ago