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:All amd apple google intel nvidia 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

128 units shown · sorted by score

#	Hardware	Tier	Score	Throughput	VRAM-fit	Ecosystem	Efficiency	Data
1	NVIDIA GeForce RTX 5090 nvidia · enthusiast · 32GB · 1 bench	S	852	500	170	200	27	Measured-near
2	NVIDIA GeForce RTX 4090 nvidia · enthusiast · 24GB · 7 bench	A	790	435	170	200	27	Measured-near
3	NVIDIA GeForce RTX 5080 nvidia · enthusiast · 16GB · 2 bench	A	752	383	140	200	29	Measured
4	NVIDIA GeForce RTX 3090 nvidia · enthusiast · 24GB · 1 bench	B	664	305	170	200	24	Measured-near
5	NVIDIA GeForce RTX 3080 16GB (Mobile) nvidia · high · 16GB · 1 bench	B	608	230	140	200	38	Measured
6	AMD Radeon RX 7900 XTX amd · enthusiast · 24GB · 1 bench	C	485	251	170	130	19	Community
7	NVIDIA GeForce RTX 3080 Ti nvidia · enthusiast · 12GB	C	456	317	110	200	25	Estimated
8	NVIDIA GeForce RTX 4080 Super nvidia · high · 16GB	C	433	256	140	200	22	Estimated
9	Apple M4 Max apple · enthusiast · 2 bench	C	392	228	0	170	63	Community
10	NVIDIA GeForce RTX 4060 Ti 16GB nvidia · mid · 16GB · 1 bench	C	371	82	140	200	14	Community
11	NVIDIA GeForce RTX 2080 Ti nvidia · enthusiast · 11GB	C	363	214	80	200	24	Estimated
12	NVIDIA GeForce RTX 3070 Ti nvidia · high · 8GB	C	358	212	80	200	20	Estimated
13	Apple M3 Max apple · enthusiast · 1 bench	C	357	160	0	170	46	Measured-near
14	NVIDIA GeForce RTX 2080 Super nvidia · high · 8GB	C	330	173	80	200	19	Estimated
15	NVIDIA GeForce GTX 1080 Ti nvidia · high · 11GB	C	327	168	80	200	19	Estimated
16	NVIDIA GeForce RTX 2060 Super nvidia · mid · 8GB	C	323	156	80	200	25	Estimated
17	NVIDIA GeForce RTX 2070 nvidia · high · 8GB	C	323	156	80	200	25	Estimated
18	NVIDIA GeForce RTX 3060 Ti nvidia · high · 8GB	C	321	156	80	200	22	Estimated
19	NVIDIA GeForce RTX 2070 Super nvidia · high · 8GB	C	319	156	80	200	20	Estimated
20	AMD Radeon RX 7900 GRE amd · high · 16GB	C	319	167	140	130	18	Estimated
21	NVIDIA GeForce RTX 3060 12GB nvidia · mid · 12GB	C	319	125	110	200	20	Estimated
22	AMD Radeon RX 6950 XT amd · enthusiast · 16GB	C	316	167	140	130	14	Estimated
23	AMD Radeon RX 6800 amd · high · 16GB	C	304	148	140	130	16	Estimated
24	AMD Radeon RX 6800 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
25	AMD Radeon RX 6900 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
26	NVIDIA GeForce GTX 1080 nvidia · mid · 8GB	D	286	111	80	200	17	Estimated
27	NVIDIA RTX PRO 6000 Blackwell nvidia · workstation · 96GB	D	280	0	200	200	0	Estimated
28	NVIDIA GB200 NVL72 nvidia · workstation · 13824GB	D	280	0	200	200	0	Estimated
29	NVIDIA B200 nvidia · workstation · 192GB	D	280	0	200	200	0	Estimated
30	NVIDIA H200 nvidia · workstation · 141GB	D	280	0	200	200	0	Estimated
31	NVIDIA H100 NVL nvidia · workstation · 188GB	D	280	0	200	200	0	Estimated
32	NVIDIA RTX 6000 Ada Generation nvidia · workstation · 48GB	D	273	0	190	200	0	Estimated
33	NVIDIA L40S nvidia · workstation · 48GB	D	273	0	190	200	0	Estimated
34	NVIDIA L40 nvidia · workstation · 48GB	D	273	0	190	200	0	Estimated
35	NVIDIA H100 PCIe nvidia · workstation · 80GB	D	273	0	190	200	0	Estimated
36	NVIDIA A40 nvidia · workstation · 48GB	D	273	0	190	200	0	Estimated
37	NVIDIA RTX A6000 (Ampere) nvidia · workstation · 48GB	D	273	0	190	200	0	Estimated
38	NVIDIA A100 80GB SXM nvidia · workstation · 80GB	D	273	0	190	200	0	Estimated
39	NVIDIA H100 SXM nvidia · workstation · 80GB	D	273	0	190	200	0	Estimated
40	NVIDIA GeForce GTX 1070 nvidia · mid · 8GB	D	270	89	80	200	16	Estimated
41	NVIDIA GeForce GTX 1070 Ti nvidia · mid · 8GB	D	268	89	80	200	14	Estimated
42	AMD Radeon RX 6750 XT amd · high · 12GB	D	265	125	110	130	14	Estimated
43	NVIDIA GeForce RTX 3050 nvidia · entry · 8GB	D	263	78	80	200	17	Estimated
44	NVIDIA GeForce GTX 1660 Super nvidia · mid · 6GB	D	261	117	30	200	26	Estimated
45	NVIDIA GeForce RTX 3090 Ti nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
46	NVIDIA GeForce RTX 5090 Mobile nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
47	NVIDIA A100 40GB nvidia · workstation · 40GB	D	259	0	170	200	0	Estimated
48	NVIDIA L4 nvidia · workstation · 24GB	D	259	0	170	200	0	Estimated
49	NVIDIA RTX 5000 Ada Generation nvidia · workstation · 32GB	D	259	0	170	200	0	Estimated
50	Razer Blade 16 (2025, RTX 5090 Mobile) nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
51	ASUS ROG Strix Scar 18 (RTX 5090 Mobile) nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
52	NVIDIA RTX A5000 nvidia · workstation · 24GB	D	259	0	170	200	0	Estimated
53	NVIDIA GeForce RTX 2060 nvidia · mid · 6GB	D	257	117	30	200	20	Estimated
54	AMD Radeon RX 6700 XT amd · high · 12GB	D	255	111	110	130	13	Estimated
55	NVIDIA GeForce GTX 1660 Ti nvidia · mid · 6GB	D	247	100	30	200	23	Estimated
56	NVIDIA GeForce RTX 5070 Ti nvidia · high · 16GB	D	238	0	140	200	0	Estimated
57	NVIDIA GeForce RTX 4080 nvidia · high · 16GB	D	238	0	140	200	0	Estimated
58	NVIDIA GeForce RTX 4070 Ti Super nvidia · high · 16GB	D	238	0	140	200	0	Estimated
59	NVIDIA GeForce RTX 5060 Ti 16GB nvidia · mid · 16GB	D	238	0	140	200	0	Estimated
60	Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB) nvidia · high · 16GB	D	238	0	140	200	0	Estimated
61	NVIDIA GeForce RTX 4090 Mobile nvidia · enthusiast · 16GB	D	238	0	140	200	0	Estimated
62	AMD Instinct MI300X amd · workstation · 192GB	D	231	0	200	130	0	Estimated
63	AMD Instinct MI250X amd · workstation · 128GB	D	231	0	200	130	0	Estimated
64	AMD Instinct MI355X amd · workstation · 288GB	D	231	0	200	130	0	Estimated
65	AMD Instinct MI325X amd · workstation · 256GB	D	231	0	200	130	0	Estimated
66	AMD Instinct MI300A (APU) amd · workstation · 128GB	D	231	0	200	130	0	Estimated
67	AMD Instinct MI210 amd · workstation · 64GB	D	224	0	190	130	0	Estimated
68	NVIDIA GeForce RTX 3050 Ti (Mobile) nvidia · mobile · 4GB	D	224	67	30	200	23	Estimated
69	Apple M4 (iPad Pro) apple · mobile	D	223	49	0	170	100	Estimated
70	NVIDIA GeForce GTX 1650 Super nvidia · entry · 4GB	D	221	67	30	200	18	Estimated
71	NVIDIA GeForce GTX 1060 6GB nvidia · entry · 6GB	D	218	67	30	200	15	Estimated
72	NVIDIA GeForce GTX 1660 nvidia · mid · 6GB	D	218	67	30	200	15	Estimated
73	NVIDIA GeForce GTX 1060 3GB nvidia · entry · 3GB	D	218	67	30	200	15	Estimated
74	NVIDIA GeForce RTX 4070 Ti nvidia · high · 12GB	D	217	0	110	200	0	Estimated
75	NVIDIA GeForce RTX 4070 nvidia · mid · 12GB	D	217	0	110	200	0	Estimated
76	NVIDIA GeForce RTX 3080 12GB nvidia · high · 12GB	D	217	0	110	200	0	Estimated
77	NVIDIA GeForce RTX 5070 nvidia · mid · 12GB	D	217	0	110	200	0	Estimated
78	NVIDIA GeForce RTX 4070 Super nvidia · mid · 12GB	D	217	0	110	200	0	Estimated
79	AMD Radeon RX 5700 XT amd · high · 8GB	D	214	130	80	80	16	Estimated
80	AMD Radeon RX 6650 XT amd · mid · 8GB	D	212	81	80	130	12	Estimated
81	AMD Radeon RX 6600 XT amd · mid · 8GB	D	208	74	80	130	13	Estimated
82	Apple A18 Pro apple · mobile	D	206	24	0	170	100	Estimated
83	NVIDIA GeForce GTX 1650 nvidia · entry · 4GB	D	204	45	30	200	16	Estimated
84	Apple A17 Pro apple · mobile	D	204	21	0	170	100	Estimated
85	AMD Radeon RX 6600 amd · mid · 8GB	D	202	65	80	130	14	Estimated
86	Apple M3 Ultra apple · enthusiast · 1 bench	D	200	35	0	170	5	Measured-near
87	NVIDIA GeForce GTX 1050 Ti nvidia · entry · 4GB	D	198	39	30	200	14	Estimated
88	NVIDIA GeForce RTX 4060 Ti 8GB nvidia · mid · 8GB	D	196	0	80	200	0	Estimated
89	NVIDIA GeForce RTX 4060 nvidia · entry · 8GB	D	196	0	80	200	0	Estimated
90	NVIDIA GeForce RTX 3080 10GB nvidia · high · 10GB	D	196	0	80	200	0	Estimated
91	NVIDIA GeForce RTX 5060 nvidia · entry · 8GB	D	196	0	80	200	0	Estimated
92	NVIDIA GeForce RTX 3070 nvidia · mid · 8GB	D	196	0	80	200	0	Estimated
93	NVIDIA GeForce RTX 5060 Ti 8GB nvidia · mid · 8GB	D	196	0	80	200	0	Estimated
94	AMD Radeon RX 7900 XT amd · enthusiast · 20GB	D	189	0	140	130	0	Estimated
95	AMD Radeon RX 7800 XT amd · high · 16GB	D	189	0	140	130	0	Estimated
96	AMD Radeon RX 9070 amd · high · 16GB	D	189	0	140	130	0	Estimated
97	AMD Radeon RX 7600 XT amd · mid · 16GB	D	189	0	140	130	0	Estimated
98	AMD Radeon RX 9070 XT amd · high · 16GB	D	189	0	140	130	0	Estimated
99	AMD Radeon RX 580 8GB amd · mid · 8GB	D	172	74	80	80	11	Estimated
100	AMD Radeon RX 7700 XT amd · mid · 12GB	D	168	0	110	130	0	Estimated
101	Intel Gaudi 2 intel · workstation · 96GB	D	168	0	200	40	0	Estimated
102	Intel Gaudi 3 intel · workstation · 128GB	D	168	0	200	40	0	Estimated
103	AMD Radeon RX 5500 XT 8GB amd · entry · 8GB	D	167	65	80	80	14	Estimated
104	AMD Radeon RX 5600 XT amd · mid · 6GB	D	158	97	30	80	18	Estimated
105	Intel Arc A770 16GB intel · mid · 16GB	D	154	0	140	80	0	Estimated
106	Framework Laptop 16 (RX 7700S) amd · mid · 8GB	D	147	0	80	130	0	Estimated
107	NVIDIA DGX Spark (Project Digits) nvidia · workstation	D	140	0	0	200	0	Estimated
108	Intel Arc B580 intel · mid · 12GB	D	133	0	110	80	0	Estimated
109	AMD Radeon 880M (Strix Point iGPU) amd · entry	D	132	30	0	130	29	Estimated
110	AMD Radeon RX 570 amd · entry · 4GB	D	131	65	30	80	12	Estimated
111	Qualcomm Snapdragon 8 Elite qualcomm · mobile	D	127	21	0	60	100	Estimated
112	AMD Ryzen AI 9 HX 370 (Strix Point) amd · pc-npu	D	127	26	0	130	26	Estimated
113	AMD Radeon 780M (Phoenix iGPU) amd · entry	D	127	26	0	130	25	Estimated
114	Qualcomm Snapdragon 8 Gen 3 qualcomm · mobile	D	123	18	0	60	98	Estimated
115	Apple M2 Ultra apple · enthusiast	D	119	0	0	170	0	Estimated
116	Apple M4 Ultra apple · enthusiast	D	119	0	0	170	0	Estimated
117	Apple M4 Pro apple · high	D	119	0	0	170	0	Estimated
118	Apple Mac Studio (M3 Ultra) apple · enthusiast	D	119	0	0	170	0	Estimated
119	MacBook Pro 16" M4 Max apple · enthusiast	D	119	0	0	170	0	Estimated
120	Apple M2 Max apple · high	D	119	0	0	170	0	Estimated
121	Apple M1 Max apple · high	D	119	0	0	170	0	Estimated
122	Apple M1 Ultra apple · enthusiast	D	119	0	0	170	0	Estimated
123	Intel Arc 140V (Lunar Lake iGPU) intel · entry	D	115	32	0	80	52	Estimated
124	Intel Arc B570 intel · mid · 10GB	D	112	0	80	80	0	Estimated
125	Google Tensor G4 google · mobile	D	106	14	0	60	77	Estimated
126	Intel Core Ultra 7 258V (Lunar Lake) intel · pc-npu	D	100	32	0	60	51	Estimated
127	Qualcomm Snapdragon X Plus qualcomm · mid	D	28	0	0	40	0	Estimated
128	Qualcomm Snapdragon X Elite qualcomm · high	D	28	0	0	40	0	Estimated

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