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 157 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:All amd apple google intel nvidia other qualcomm

VRAM:All ≤8GB 9–16GB 17–24GB 25–48GB 49–96GB 97GB+

Tier:All S A B C D

Data:All Measured Measured-near Community Extrapolated Estimated

41 units shown · sorted by score

#	Hardware	Tier	Score	Throughput	VRAM-fit	Ecosystem	Efficiency	Data
1	AMD Instinct MI355X amd · workstation · 288GB	B	626	500	200	130	64	Estimated
2	AMD Instinct MI350X amd · workstation · 288GB	B	626	500	200	130	64	Estimated
3	AMD Instinct MI300X amd · workstation · 192GB	B	621	500	200	130	57	Estimated
4	AMD Instinct MI300A (APU) amd · workstation · 128GB	B	620	500	200	130	56	Estimated
5	AMD Instinct MI325X amd · workstation · 256GB	B	615	500	200	130	48	Estimated
6	AMD Instinct MI250X amd · workstation · 128GB	B	614	500	200	130	47	Estimated
7	AMD Instinct MI210 amd · workstation · 64GB	B	587	475	190	130	44	Estimated
8	AMD Radeon RX 7900 XTX amd · enthusiast · 24GB	C	420	278	170	130	22	Estimated
9	AMD Radeon RX 7900 XT amd · enthusiast · 20GB	C	365	232	140	130	20	Estimated
10	AMD Radeon RX 9060 XT amd · mid · 16GB	C	339	186	140	130	28	Estimated
11	AMD Radeon RX 9070 XT amd · high · 16GB	C	332	187	140	130	17	Estimated
12	AMD Radeon RX 9070 amd · high · 16GB	C	332	181	140	130	23	Estimated
13	AMD Radeon RX 7800 XT amd · high · 16GB	C	329	181	140	130	19	Estimated
14	AMD Radeon RX 7900 GRE amd · high · 16GB	C	319	167	140	130	18	Estimated
15	AMD Radeon RX 6950 XT amd · enthusiast · 16GB	C	316	167	140	130	14	Estimated
16	AMD Radeon RX 6800 amd · high · 16GB	C	304	148	140	130	16	Estimated
17	AMD Radeon RX 6800 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
18	AMD Radeon RX 6900 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
19	AMD Ryzen AI Max+ 395 (Strix Halo) amd · workstation	D	288	74	190	130	17	Estimated
20	AMD Radeon RX 9070 GRE amd · high · 12GB	D	267	125	110	130	16	Estimated
21	AMD Radeon RX 7700 XT amd · mid · 12GB	D	265	125	110	130	14	Estimated
22	AMD Radeon RX 6750 XT amd · high · 12GB	D	265	125	110	130	14	Estimated
23	AMD Radeon RX 7600 XT amd · mid · 16GB	D	256	84	140	130	12	Estimated
24	AMD Radeon RX 6700 XT amd · high · 12GB	D	255	111	110	130	13	Estimated
25	AMD Ryzen AI 9 HX 370 (Strix Point) amd · pc-npu	D	246	26	170	130	26	Estimated
26	AMD Radeon RX 5700 XT amd · high · 8GB	D	214	130	80	80	16	Estimated
27	AMD Radeon RX 6650 XT amd · mid · 8GB	D	212	81	80	130	12	Estimated
28	AMD Radeon RX 6600 XT amd · mid · 8GB	D	208	74	80	130	13	Estimated
29	AMD Radeon RX 6600 amd · mid · 8GB	D	202	65	80	130	14	Estimated
30	AMD Radeon RX 580 8GB amd · mid · 8GB	D	172	74	80	80	11	Estimated
31	AMD Radeon RX 5500 XT 8GB amd · entry · 8GB	D	167	65	80	80	14	Estimated
32	AMD EPYC 9005 (Zen 5, Turin) amd · workstation	D	161	178	0	40	12	Estimated
33	AMD Radeon RX 5600 XT amd · mid · 6GB	D	158	97	30	80	18	Estimated
34	AMD Ryzen AI Halo amd · workstation	D	155	74	0	130	17	Estimated
35	HP ZBook Ultra G1a (Ryzen AI Max+ PRO 395) amd · workstation	D	155	74	0	130	17	Estimated
36	Framework Desktop (Ryzen AI Max+ 395) amd · workstation	D	153	74	0	130	15	Estimated
37	GMKtec EVO-X2 (Ryzen AI Max+ 395) amd · workstation	D	153	74	0	130	15	Estimated
38	Framework Laptop 16 (RX 7700S) amd · mid · 8GB	D	147	0	80	130	0	Estimated
39	AMD Radeon 880M (Strix Point iGPU) amd · entry	D	132	30	0	130	29	Estimated
40	AMD Radeon RX 570 amd · entry · 4GB	D	131	65	30	80	12	Estimated
41	AMD Radeon 780M (Phoenix iGPU) amd · entry	D	127	26	0	130	25	Estimated

BLK · BUY · AMAZON

Shop GPUs & AI hardware on Amazon:GPU categoryRTX 4090RTX 5090Apple M-seriesAI mini-PCs

Amazon search links — we may earn a small commission at no extra cost to you. How we make money.

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.

> RunLocalAI Score

RunLocalAI Score