Developer Tools●●Solid
Slopsome – a VRAM fit calculator and tok/s database for local LLMs
VRAM calculator with crowd-sourced tok/s benchmarks when model cards already exist.
Niche GemSolve My Problem
NexAIGuy
306d ago
Back to browse
Quant Picker – which GGUF file fits your model and machine
by ermantrout·Jun 13, 2026·20 points·0 comments
AI Analysis
●●SolidSolve My ProblemNiche Gem
Finally answers the GGUF quant question everyone asks in Discord.
Strengths
- •Shows the actual math instead of hiding it — educational and transparent
- •Shareable URLs preserve your model and hardware selections
- •KV cache precision options account for real context budget tradeoffs
Weaknesses
- •File sizes computed from bits-per-weight, not scraped from Hugging Face
- •Niche audience — only matters if you're already running local models
Category
Target Audience
Local LLM runners and hobbyists
Similar Projects
Productivity●Mid
Can this model run on my Mac mini?
Clean hardware-model compatibility checker, but solves a narrow, one-time lookup problem.
CozyEye Candy
mkagenius
203mo ago
Developer Tools●Mid
Host any GGUF model in one command
Ollama and llama.cpp server already do this with more maturity and model support.
Ship It
gauravvij137
302mo ago
Education●Mid
Llama.cpp Tutorial 2026: Run GGUF Models Locally on CPU and GPU
Useful tutorial, but llama.cpp docs and Ollama already cover most of this.
Niche Gem
anju-kushwaha
1342mo ago
AI/ML●●Solid
Will It Fit? – Opinionated Normal People Llama.cpp VRAM Estimator
Opinionated llama.cpp VRAM calculator that outputs ready-to-run server commands.
Solve My ProblemShip It
hypfer
4115d 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
104mo ago