RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
← Back to Will-it-run

Custom build engine

Describe your build — any GPUs, CPU, RAM, OS, runtime, use case. We'll compute effective VRAM honestly, recommend a runtime, and tell you which models fit comfortably, which are borderline, and which aren't practical.

Total VRAM ≠ pooled VRAM. We never sum VRAM unless the silicon truly pools (Apple unified memory). We always explain why effective is lower than total.

Calculations follow the RunLocalAI Will-It-Run Framework: effective VRAM, model working set, runtime constraints, fit tiers, and measured-vs-estimated evidence labels.

Describe your build

Add GPUs, set CPU/RAM/OS, optionally pick a runtime + use case. URL updates as you change fields — share a build by copying the URL.

Build summary

Total VRAM
96 GB
Effective VRAM
~75 GB
range 71-77 GB
Topology
single node multi gpu
pcie
Setup difficulty
advanced
speed penalty ~18%
Why effective VRAM is lower than total

4× NVIDIA GeForce RTX 3090 = 96 GB total VRAM, but without NVLink, cross-card bandwidth is PCIe-bound (~32 GB/s vs NVLink ~112 GB/s). With tensor-parallelism, each card holds ~1/4 of the model weights and replicates activations + KV cache. After 15% TP overhead, effective model capacity is ~75 GB. Largest single tensor on one card is ~22 GB.

Measured evidence on this hardware

Publicly inspectable measured rows for the selected hardware slug(s). Exact measured rows calibrate the fit table instead of leaving it as pure VRAM estimation.

No publicly inspectable benchmark rows are attached to this exact hardware yet. The engine will still calculate fit and runtime, but speed rows will remain estimated.

Recommended runtime

Best engine for this topology + skill level + use case.

vLLM
primary
involved

Tensor-parallel across NVLink/PCIe — works on every recent consumer + datacenter pair. AWQ-INT4 + 70B fits dual 3090 / dual 4090 cleanly.

ExLlamaV2
alternative
involved

Single-stream king. EXL2 4.0bpw + 70B fits dual 3090 with NVLink and beats vLLM on solo-user throughput.

llama.cpp
alternative
moderate

Layer-split via --tensor-split is the experimentation-friendly path. Worse throughput than vLLM but easier to debug.

WORKLOAD PROFILE
FITS
Qwen 2.5 Math 72B @ Q4_K_M, 4K context on NVIDIA GeForce RTX 3090
0 GB75 GBVRAM ceiling
Weights41 GB
KV cache18 GB
Activations2.1 GB
Runtime1.8 GB
Headroom12 GB
ESTIMATED DECODE RATE
16 tok/s
Bandwidth-derived estimate · efficiency 0.70. Real-world rates land within ±20% on well-tuned runtimes.
16 tokens per second02550100150

Models that fit your build

315 models considered. Categorized by headroom at the recommended quant + a sensible context for your use case.

Comfortable
24 models · ≥15% headroom
ModelParamsQuantVRAM est.ContextEvidenceNote
Qwen 2.5 Math 72B72BQ4_K_M61.1 GB4,096No measured row yetFits cleanly at Q4_K_M + 4,096 ctx with 19% headroom.
Molmo 72B72BQ4_K_M61.1 GB4,096No measured row yetFits cleanly at Q4_K_M + 4,096 ctx with 19% headroom.
Llama 3.3 70B Instruct70BQ5_K_M52 GB8,192No measured row yetFits cleanly at Q5_K_M + 8,192 ctx with 31% headroom.
Jamba 1.5 Mini52BQ4_K_M57.5 GB8,192No measured row yetFits cleanly at Q4_K_M + 8,192 ctx with 23% headroom.
Nemotron 3 Super 49B49BAWQ-INT453.9 GB8,192No measured row yetFits cleanly at AWQ-INT4 + 8,192 ctx with 28% headroom.
Mixtral 8x7B Instruct47BQ5_K_M58.2 GB8,192No measured row yetFits cleanly at Q5_K_M + 8,192 ctx with 22% headroom.
Mixtral 8X7B Instruct v0.1 GPTQ47BQ4_K_M50.3 GB8,192No measured row yetFits cleanly at Q4_K_M + 8,192 ctx with 33% headroom.
ALIA 40b instruct 260140BQ4_K_M43.1 GB8,192No measured row yetComfortable fit with 43% headroom — room to extend context or run alongside other workloads.
Falcon 40B Instruct40BQ4_K_M28.1 GB2,048No measured row yetComfortable fit with 63% headroom — room to extend context or run alongside other workloads.
Qwen 3.6 35B-A3B (MTP)35BQ8_056.6 GB8,192No measured row yetFits cleanly at Q8_0 + 8,192 ctx with 25% headroom.
Aya 23 35B35BQ4_K_M39.6 GB8,192No measured row yetComfortable fit with 47% headroom — room to extend context or run alongside other workloads.
Mihenk LLM v2 35B (Turkish Financial)35BQ4_K_M37.8 GB8,192No measured row yetComfortable fit with 50% headroom — room to extend context or run alongside other workloads.
Command R 35B35BQ4_K_M39.6 GB8,192No measured row yetComfortable fit with 47% headroom — room to extend context or run alongside other workloads.
Phind CodeLlama 34B v234BQ4_K_M38 GB8,192No measured row yetComfortable fit with 49% headroom — room to extend context or run alongside other workloads.
Yi 1.5 34B34BQ4_K_M38 GB8,192No measured row yetComfortable fit with 49% headroom — room to extend context or run alongside other workloads.
DeepSeek Coder V333BAWQ-INT436.5 GB8,192No measured row yetComfortable fit with 51% headroom — room to extend context or run alongside other workloads.
EXAONE 3.5 32B Instruct32BQ4_K_M34.5 GB8,192No measured row yetComfortable fit with 54% headroom — room to extend context or run alongside other workloads.
EXAONE 3.5 32B Instruct AWQ32BQ4_K_M34.5 GB8,192No measured row yetComfortable fit with 54% headroom — room to extend context or run alongside other workloads.
Qwen 2.5 32B Instruct32BQ8_051.7 GB8,192No measured row yetFits cleanly at Q8_0 + 8,192 ctx with 31% headroom.
Magistral 32B32BAWQ-INT436 GB8,192No measured row yetComfortable fit with 52% headroom — room to extend context or run alongside other workloads.
Aya Expanse 32B32BAWQ-INT436 GB8,192No measured row yetComfortable fit with 52% headroom — room to extend context or run alongside other workloads.
QwQ 32B Preview32BQ4_K_M36 GB8,192No measured row yetComfortable fit with 52% headroom — room to extend context or run alongside other workloads.
DeepSeek R1 Distill Qwen 3 32B32BAWQ-INT436 GB8,192No measured row yetComfortable fit with 52% headroom — room to extend context or run alongside other workloads.
EXAONE 4.0.1 32B32BQ4_K_M34.5 GB8,192No measured row yetComfortable fit with 54% headroom — room to extend context or run alongside other workloads.
Borderline
1 models · tight, may need quant downgrade
ModelParamsQuantVRAM est.ContextEvidenceNote
Qwen 3.6 27B (MTP)27BFP1670.2 GB8,192No measured row yetTight fit at FP16 — only 6% headroom. KV cache for longer context will OOM. Cap context tighter or drop one quant level.
Not practical
16 models · oversize for this build
ModelParamsQuantVRAM est.ContextEvidenceNote
Dolphin 3 Llama 3.3 70B70BAWQ-INT477 GB8,192No measured row yet~77.0 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
DeepSeek R1 Distill Llama 70B70BQ4_K_M77 GB8,192No measured row yet~77.0 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Llama 3.1 70B Instruct70BQ4_K_M77 GB8,192No measured row yet~77.0 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Tulu 3 70B70BQ4_K_M77 GB8,192No measured row yet~77.0 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Hermes 3 Llama 3.1 70B70BQ4_K_M77 GB8,192No measured row yet~77.0 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Hermes 4 Llama 3.3 70B70BAWQ-INT477 GB8,192No measured row yet~77.0 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Llama 3.1 Nemotron 70B Instruct70BQ4_K_M77 GB8,192No measured row yet~77.0 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Hermes 4 70B FP870BQ4_K_M75.4 GB8,192No measured row yet~75.4 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 1%. Drop quant or move to a larger build.
Llama 4 70B70BAWQ-INT477 GB8,192No measured row yet~77.0 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
OpenBioLLM Llama 3 70B70BQ4_K_M79.1 GB8,192No measured row yet~79.1 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 5%. Drop quant or move to a larger build.
EVA Llama 3.3 70B70BAWQ-INT477 GB8,192No measured row yet~77.0 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 3%. Drop quant or move to a larger build.
Qwen 2.5 72B Instruct72BQ4_K_M79.1 GB8,192No measured row yet~79.1 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 5%. Drop quant or move to a larger build.
Qwen 2.5-VL 72B72BAWQ-INT480.1 GB8,192No measured row yet~80.1 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 7%. Drop quant or move to a larger build.
InternVL 2.5 78B78BQ4_K_M86.3 GB8,192No measured row yet~86.3 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 15%. Drop quant or move to a larger build.
Llama 3.2 90B Vision90BAWQ-INT499.6 GB8,192No measured row yet~99.6 GB needed at AWQ-INT4 + 8,192 ctx — overshoots effective VRAM by 33%. Drop quant or move to a larger build.
Llama 3.2 90B Vision Instruct90BQ4_K_M98.6 GB8,192No measured row yet~98.6 GB needed at Q4_K_M + 8,192 ctx — overshoots effective VRAM by 31%. Drop quant or move to a larger build.

Related

Multi-GPU buying guide →

NVLink vs PCIe, tensor- vs pipeline-parallel, mixed-card honesty.

Hardware combinations →

Curated multi-GPU / cluster setups with effective-VRAM math.

Setup path-finder →

OS + runtime install commands for your stack.

Compatibility matrix →

Runtime × OS × hardware support truth table.

Shopping a full build instead of a single card?

If you're sizing a fresh AI build (not just a card to drop into an existing system), the build-budget walkthroughs cover the whole BOM honestly: AI PC build under $1,000 or AI PC build under $2,000 cover the realistic 2026 budget tiers.

Vertical-fit shopping? AI PC for students covers the budget + portability tradeoffs; AI PC for developers covers the coding workflow specifics; AI PC for small business covers the document-RAG / always-on machine.

Form-factor first? See best laptop for local AI, best Mac for local AI, best mini PC for local AI, or best used GPU for local AI.

See something off?Submit a benchmark·Report outdated·Suggest a correctionWe read every submission. Editorial review takes 1-7 days.