{"uid":"cap_4BdAE9wH8XKoa5Iaxdr1q","slug":"salt19-model-memory-fit-calculator-c8dff1e4","name":"SALT19 Model Memory Fit Calculator","description":"SALT19 is an independent applied AI systems lab behind EvoMind governed cognition, the MCP-native Agent Utility Grid, the ARCS research community, AeroClear UAS flight intelligence, and practical software for real-world work.","url":"https://api.salt19.com/v1/model-memory-fit","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"vram_gb":{"type":"number","maximum":10000,"minimum":0.1},"parameter_count_b":{"type":"number","maximum":10000,"minimum":0.01},"quantization_bits":{"type":"number","maximum":32,"minimum":1},"runtime_overhead_ratio":{"type":"number","maximum":2,"minimum":0}}},"responseSchema":{"type":"json","example":{"verdict":"FIT","vram_gib":11,"limitations":["KV cache and architecture-specific buffers are not modeled"],"headroom_gib":7.25,"estimated_total_gib":3.75,"estimated_weight_gib":3.26}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"down","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JOyRmO1GJFv3x4TmyCxGv","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Estimates whether an LLM model will fit in a given VRAM budget, returning a FIT/NO-FIT verdict with estimated memory breakdown and headroom.","exampleAgentPrompt":"Will a 7B parameter model at 4-bit quantization fit in my 11 GiB VRAM GPU? Assume a runtime overhead ratio of 0.1 and give me the memory breakdown.","exampleUseCases":[{"title":"Pre-deployment VRAM feasibility check","prompt":"I'm about to pull a 13B parameter model quantized to 8-bit onto a GPU with 16 GiB VRAM. Can you check if it will actually fit and tell me how much headroom I'd have left?"},{"title":"Consumer GPU hobby build planning","prompt":"I want to self-host a 7B model at 4-bit quantization on my gaming PC which has 8 GiB of VRAM. Will it fit, and what's the estimated memory breakdown?"},{"title":"Enterprise multi-GPU sizing for 70B model","prompt":"We're evaluating whether a 70B parameter model at 8-bit quantization fits on an 80 GiB A100 with a runtime overhead ratio of 0.15 — can you run the memory fit calculation?"}],"resultDescription":"A JSON object containing a FIT or NO-FIT verdict, estimated model weight in GiB, estimated total VRAM usage in GiB (including overhead), headroom in GiB remaining after loading, and a list of known modeling limitations (e.g. KV cache and architecture-specific buffers are not modeled).","failureModes":["Invalid or out-of-range vram_gb (below 0.1 or above 10000) causes validation error","parameter_count_b below 0.01 or above 10000 rejected","quantization_bits outside 1–32 range rejected","runtime_overhead_ratio outside 0–2 range rejected","Missing required fields may return 400 or partial computation","Estimate may be inaccurate for models with non-standard architectures due to KV cache and buffer exclusions"],"whenToPreferThis":"Choose this endpoint when you need a fast, programmatic check of whether a specific quantized LLM will fit in a known VRAM budget before downloading or deploying the model. It is purpose-built for LLM memory estimation with quantization awareness, unlike generic hardware calculators. Prefer it over manual formulas when you need structured output (verdict + headroom) that an agent can act on automatically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T20:28:52.797Z","isFirstParty":false}