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
301d ago
Back to browse
Will It Fit? – Opinionated Normal People Llama.cpp VRAM Estimator
by hypfer·Jun 4, 2026·4 points·1 comment
AI Analysis
●●SolidSolve My ProblemShip It
Opinionated llama.cpp VRAM calculator that outputs ready-to-run server commands.
Strengths
- •Includes MTP draft KV and compute buffers missed by generic calculators.
- •Pessimistic estimates prevent OOM crashes better than optimistic theoretical minimums.
- •Direct command generation saves digging through llama.cpp documentation for flags.
Weaknesses
- •Curated model list limits utility for niche or custom fine-tunes.
- •Single GPU assumption excludes multi-GPU setups common in high-end rigs.
Category
Target Audience
Local LLM hobbyists, developers running inference on consumer hardware
Similar To
Hugging Face VRAM Calculators · Llama.cpp Documentation · Text Generation WebUI
Similar Projects
AI/ML●●Solid
Best setup local LLM found for a 5090 (llama.cpp fork + turboquant)
450k context on 32GB VRAM using turboquant KV cache compression.
Big BrainNiche Gem
utopman
228d ago
Productivity●Mid
Simple CBM calculator for shipping and freight
Multi-item container fit calculator that actually saves state locally.
Solve My ProblemCozy
distartin
503mo ago
AI/ML●●●Banger
TurboPrefill – Multi-GPU prefill acceleration for llama.cpp
2x prefill speedup on 12k+ token contexts by treating GPUs like a production line.
Big BrainWizardry
trykhlieb
2011d ago
Developer Tools●●Solid
Run Llama.cpp In-Process from Java with Project Panama FFM
Panama FFM beats JNI for in-process llama.cpp - no sidecar, no HTTP, no native install.
Big BrainNiche Gem
deemwar
6010d ago
Developer Tools●●●Banger
A single CLI to manage llama.cpp/vLLM/Ollama models
Finally one CLI for Ollama, llama.cpp, and vLLM instead of three separate tools.
Solve My ProblemSlick
everlier
213mo ago