AI/ML●Mid
Local LLM Hardware Calculator
VRAM calculator with formulas visible, but many free alternatives exist.
Solve My Problem
ermantrout
301mo ago
Back to browse
Hardware requirement calculator for local LLMs
by gkrishna·Aug 5, 2026·1 point·0 comments
AI Analysis
●●SolidSolve My ProblemNiche Gem
Instantly calculates if a specific model quantization fits your GPU VRAM.
Strengths
- •Supports an exhaustive list of modern models including Qwen3 and DeepSeek variants.
- •Accounts for KV cache quantization impact on long-context memory usage.
- •Includes bandwidth-based throughput estimates alongside raw capacity checks.
Weaknesses
- •Relies on theoretical TFLOPS rather than实测 benchmarked latency numbers.
- •Does not account for multi-GPU tensor parallelism overhead complexities.
Category
Target Audience
Developers and hobbyists running local large language models
Similar To
llama.cpp server logs · Hugging Face model cards
Similar Projects
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
301mo 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
412mo ago
Developer Tools●●Solid
In-browser real LLM token counter and cost estimation
Local tokenizer execution beats sending text to external counters.
CozySolve My Problem
angelmm
311mo ago
Developer Tools●Mid
A tool to calculate LLM model API costs when coding
LLM cost calculator with current pricing, but spreadsheets and existing tools already do this.
Solve My Problem
canxerian
423mo ago
AI/ML●Mid
A calculator to expose the hidden infrastructural costs behind RAG
Breaks down hidden RAG costs like vector storage overhead and HNSW indexing fees.
Solve My Problem
abarth23
203mo ago