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

64 units shown · sorted by score

#HardwareTierScoreThroughputVRAM-fitEcosystemEfficiencyData
1NVIDIA GeForce RTX 3080 Ti
nvidia · enthusiast · 12GB
C45631711020025Estimated
2NVIDIA GeForce RTX 4080 Super
nvidia · high · 16GB
C43325614020022Estimated
3NVIDIA GeForce RTX 2080 Ti
nvidia · enthusiast · 11GB
C3632148020024Estimated
4NVIDIA GeForce RTX 3070 Ti
nvidia · high · 8GB
C3582128020020Estimated
5NVIDIA GeForce RTX 2080 Super
nvidia · high · 8GB
C3301738020019Estimated
6NVIDIA GeForce GTX 1080 Ti
nvidia · high · 11GB
C3271688020019Estimated
7NVIDIA GeForce RTX 2060 Super
nvidia · mid · 8GB
C3231568020025Estimated
8NVIDIA GeForce RTX 2070
nvidia · high · 8GB
C3231568020025Estimated
9NVIDIA GeForce RTX 3060 Ti
nvidia · high · 8GB
C3211568020022Estimated
10NVIDIA GeForce RTX 2070 Super
nvidia · high · 8GB
C3191568020020Estimated
11NVIDIA GeForce RTX 3060 12GB
nvidia · mid · 12GB
C31912511020020Estimated
12NVIDIA GeForce GTX 1080
nvidia · mid · 8GB
D2861118020017Estimated
13NVIDIA RTX PRO 6000 Blackwell
nvidia · workstation · 96GB
D28002002000Estimated
14NVIDIA GB200 NVL72
nvidia · workstation · 13824GB
D28002002000Estimated
15NVIDIA B200
nvidia · workstation · 192GB
D28002002000Estimated
16NVIDIA H200
nvidia · workstation · 141GB
D28002002000Estimated
17NVIDIA H100 NVL
nvidia · workstation · 188GB
D28002002000Estimated
18NVIDIA RTX 6000 Ada Generation
nvidia · workstation · 48GB
D27301902000Estimated
19NVIDIA L40S
nvidia · workstation · 48GB
D27301902000Estimated
20NVIDIA L40
nvidia · workstation · 48GB
D27301902000Estimated
21NVIDIA H100 PCIe
nvidia · workstation · 80GB
D27301902000Estimated
22NVIDIA A40
nvidia · workstation · 48GB
D27301902000Estimated
23NVIDIA RTX A6000 (Ampere)
nvidia · workstation · 48GB
D27301902000Estimated
24NVIDIA A100 80GB SXM
nvidia · workstation · 80GB
D27301902000Estimated
25NVIDIA H100 SXM
nvidia · workstation · 80GB
D27301902000Estimated
26NVIDIA GeForce GTX 1070
nvidia · mid · 8GB
D270898020016Estimated
27NVIDIA GeForce GTX 1070 Ti
nvidia · mid · 8GB
D268898020014Estimated
28NVIDIA GeForce RTX 3050
nvidia · entry · 8GB
D263788020017Estimated
29NVIDIA GeForce GTX 1660 Super
nvidia · mid · 6GB
D2611173020026Estimated
30NVIDIA GeForce RTX 3090 Ti
nvidia · enthusiast · 24GB
D25901702000Estimated
31NVIDIA GeForce RTX 5090 Mobile
nvidia · enthusiast · 24GB
D25901702000Estimated
32NVIDIA A100 40GB
nvidia · workstation · 40GB
D25901702000Estimated
33NVIDIA L4
nvidia · workstation · 24GB
D25901702000Estimated
34NVIDIA RTX 5000 Ada Generation
nvidia · workstation · 32GB
D25901702000Estimated
35Razer Blade 16 (2025, RTX 5090 Mobile)
nvidia · enthusiast · 24GB
D25901702000Estimated
36ASUS ROG Strix Scar 18 (RTX 5090 Mobile)
nvidia · enthusiast · 24GB
D25901702000Estimated
37NVIDIA RTX A5000
nvidia · workstation · 24GB
D25901702000Estimated
38NVIDIA GeForce RTX 2060
nvidia · mid · 6GB
D2571173020020Estimated
39NVIDIA GeForce GTX 1660 Ti
nvidia · mid · 6GB
D2471003020023Estimated
40NVIDIA GeForce RTX 5070 Ti
nvidia · high · 16GB
D23801402000Estimated
41NVIDIA GeForce RTX 4080
nvidia · high · 16GB
D23801402000Estimated
42NVIDIA GeForce RTX 4070 Ti Super
nvidia · high · 16GB
D23801402000Estimated
43NVIDIA GeForce RTX 5060 Ti 16GB
nvidia · mid · 16GB
D23801402000Estimated
44Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB)
nvidia · high · 16GB
D23801402000Estimated
45NVIDIA GeForce RTX 4090 Mobile
nvidia · enthusiast · 16GB
D23801402000Estimated
46NVIDIA GeForce RTX 3050 Ti (Mobile)
nvidia · mobile · 4GB
D224673020023Estimated
47NVIDIA GeForce GTX 1650 Super
nvidia · entry · 4GB
D221673020018Estimated
48NVIDIA GeForce GTX 1060 6GB
nvidia · entry · 6GB
D218673020015Estimated
49NVIDIA GeForce GTX 1660
nvidia · mid · 6GB
D218673020015Estimated
50NVIDIA GeForce GTX 1060 3GB
nvidia · entry · 3GB
D218673020015Estimated
51NVIDIA GeForce RTX 4070 Ti
nvidia · high · 12GB
D21701102000Estimated
52NVIDIA GeForce RTX 4070
nvidia · mid · 12GB
D21701102000Estimated
53NVIDIA GeForce RTX 3080 12GB
nvidia · high · 12GB
D21701102000Estimated
54NVIDIA GeForce RTX 5070
nvidia · mid · 12GB
D21701102000Estimated
55NVIDIA GeForce RTX 4070 Super
nvidia · mid · 12GB
D21701102000Estimated
56NVIDIA GeForce GTX 1650
nvidia · entry · 4GB
D204453020016Estimated
57NVIDIA GeForce GTX 1050 Ti
nvidia · entry · 4GB
D198393020014Estimated
58NVIDIA GeForce RTX 4060 Ti 8GB
nvidia · mid · 8GB
D1960802000Estimated
59NVIDIA GeForce RTX 4060
nvidia · entry · 8GB
D1960802000Estimated
60NVIDIA GeForce RTX 3080 10GB
nvidia · high · 10GB
D1960802000Estimated
61NVIDIA GeForce RTX 5060
nvidia · entry · 8GB
D1960802000Estimated
62NVIDIA GeForce RTX 3070
nvidia · mid · 8GB
D1960802000Estimated
63NVIDIA GeForce RTX 5060 Ti 8GB
nvidia · mid · 8GB
D1960802000Estimated
64NVIDIA DGX Spark (Project Digits)
nvidia · workstation
D140002000Estimated
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.