RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Operator-grade instrument for local-AI hardware intelligence. Hand-written verdicts. Real benchmarks. Reproducible commands.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
  • Will it run?
GUIDES
  • Best GPU
  • Best laptop
  • Best Mac
  • Best used GPU
  • Best budget GPU
  • Best GPU for Ollama
  • Best GPU for SD
  • AI PC build $2K
  • CUDA vs ROCm
  • 16 vs 24 GB
  • Compare hardware
  • Custom compare
REF
  • Systems
  • Ecosystem maps
  • Pillar guides
  • Methodology
  • Glossary
  • Errors KB
  • Troubleshooting
  • Resources
  • Public API
EDITOR
  • About
  • About the author
  • Changelog
  • Latest
  • Updates
  • Submit benchmark
  • Send feedback
  • Trust
  • Editorial policy
  • How we make money
  • 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 →

SYS · ONLINEUPTIME · 100%2026 · operator-owned
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Hardware
  4. /Leaderboard
BLK · LEADERBOARD

> RunLocalAI Score

Every catalog hardware unit ranked by composite score (0–1000): measured tok/s, VRAM fit, ecosystem support, perf-per-watt. 2 of 128 ranks anchored to a measured benchmark — the rest are honestly flagged as extrapolated or estimated.

Methodology: /methodology · Run your own: curl -fsSL runlocalai.co/bench.mjs -o bench.mjs && node bench.mjs

Vendor:Allamdapplegoogleintelnvidiaqualcomm
VRAM:All≤8GB9–16GB17–24GB25–48GB49–96GB97GB+
Tier:AllSABCD
Data:AllMeasuredMeasured-nearCommunityExtrapolatedEstimated

20 units shown · sorted by score

#HardwareTierScoreThroughputVRAM-fitEcosystemEfficiencyData
1AMD Radeon RX 7900 XTX
amd · enthusiast · 24GB · 1 bench
C48525117013019Community
2NVIDIA GeForce RTX 3080 Ti
nvidia · enthusiast · 12GB
C45631711020025Estimated
3NVIDIA GeForce RTX 4080 Super
nvidia · high · 16GB
C43325614020022Estimated
4Apple M4 Max
apple · enthusiast · 2 bench
C392228017063Community
5NVIDIA GeForce RTX 4060 Ti 16GB
nvidia · mid · 16GB · 1 bench
C3718214020014Community
6NVIDIA GeForce RTX 2080 Ti
nvidia · enthusiast · 11GB
C3632148020024Estimated
7NVIDIA GeForce RTX 3070 Ti
nvidia · high · 8GB
C3582128020020Estimated
8Apple M3 Max
apple · enthusiast · 1 bench
C357160017046Measured-near
9NVIDIA GeForce RTX 2080 Super
nvidia · high · 8GB
C3301738020019Estimated
10NVIDIA GeForce GTX 1080 Ti
nvidia · high · 11GB
C3271688020019Estimated
11NVIDIA GeForce RTX 2060 Super
nvidia · mid · 8GB
C3231568020025Estimated
12NVIDIA GeForce RTX 2070
nvidia · high · 8GB
C3231568020025Estimated
13NVIDIA GeForce RTX 3060 Ti
nvidia · high · 8GB
C3211568020022Estimated
14NVIDIA GeForce RTX 2070 Super
nvidia · high · 8GB
C3191568020020Estimated
15AMD Radeon RX 7900 GRE
amd · high · 16GB
C31916714013018Estimated
16NVIDIA GeForce RTX 3060 12GB
nvidia · mid · 12GB
C31912511020020Estimated
17AMD Radeon RX 6950 XT
amd · enthusiast · 16GB
C31616714013014Estimated
18AMD Radeon RX 6800
amd · high · 16GB
C30414814013016Estimated
19AMD Radeon RX 6800 XT
amd · enthusiast · 16GB
C30214814013014Estimated
20AMD Radeon RX 6900 XT
amd · enthusiast · 16GB
C30214814013014Estimated
Get monthly local AI changes

Monthly recap of local-AI changes. No spam, unsubscribe with one click.

HOW THE SCORE IS DERIVED
Throughput · 0–500

Steady-state tok/s on a representative 7B/8B Q4 model. Measured from real benchmark rows, or extrapolated from VRAM bandwidth × runtime-stack efficiency.

VRAM-fit · 0–200

How comfortably the rig holds 7B / 32B / 70B class models. Apple unified memory counts; NPU/SoC system RAM counts.

Ecosystem · 0–200

CUDA / MLX / ROCm / Vulkan reach. Real-world friction the operator hits when installing tools.

Efficiency · 0–100

Tok/s per watt. Mobile / NPU class scores well; dense desktop GPUs trade efficiency for absolute throughput.

A confidence multiplier (1.0 measured · 0.85 extrapolated · 0.7 estimated) discounts the headline so we don't pretend to know more than we do. Score is recomputed on every page load against the latest catalog + benchmark data — submit your own run with runlocalai-bench --submit --hardware your-rig to firm up the numbers.