BLK · LEADERBOARD

RunLocalAI Score

Every catalog hardware unit ranked by composite score (0–1000): measured tok/s, VRAM fit, ecosystem support, perf-per-watt. 0 of 133 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

133 units shown · sorted by score

#	Hardware	Tier	Score	Throughput	VRAM-fit	Ecosystem	Efficiency	Data
1	NVIDIA H100 NVL nvidia · workstation · 94GB	B	690	500	190	200	95	Estimated
2	NVIDIA H200 NVL (PCIe) nvidia · workstation · 141GB	B	684	500	200	200	77	Estimated
3	NVIDIA H200 nvidia · workstation · 141GB	B	676	500	200	200	66	Estimated
4	NVIDIA H100 PCIe nvidia · workstation · 80GB	B	662	500	190	200	55	Estimated
5	NVIDIA A100 80GB SXM nvidia · workstation · 80GB	B	657	500	190	200	49	Estimated
6	NVIDIA H100 SXM nvidia · workstation · 80GB	B	655	500	190	200	46	Estimated
7	NVIDIA RTX PRO 6000 Blackwell nvidia · workstation · 96GB	B	650	500	200	200	29	Estimated
8	AMD Instinct MI300A (APU) amd · workstation · 128GB	B	635	500	200	130	77	Estimated
9	NVIDIA A100 40GB nvidia · workstation · 40GB	B	635	500	170	200	37	Estimated
10	NVIDIA RTX PRO 5000 Blackwell 48GB nvidia · workstation · 48GB	B	631	468	190	200	43	Estimated
11	NVIDIA GeForce RTX 5090 nvidia · enthusiast · 32GB	B	630	500	170	200	30	Estimated
12	AMD Instinct MI300X amd · workstation · 192GB	B	621	500	200	130	57	Estimated
13	Apple M5 Ultra apple · enthusiast	B	621	487	200	170	30	Estimated
14	AMD Instinct MI250X amd · workstation · 128GB	B	617	500	200	130	51	Estimated
15	AMD Instinct MI325X amd · workstation · 256GB	B	615	500	200	130	48	Estimated
16	AMD Instinct MI355X amd · workstation · 288GB	B	613	500	200	130	46	Estimated
17	AMD Instinct MI210 amd · workstation · 64GB	B	579	464	190	130	43	Estimated
18	Intel Gaudi 2 intel · workstation · 96GB	B	536	500	200	40	26	Estimated
19	Intel Gaudi 3 intel · workstation · 128GB	B	536	500	200	40	26	Estimated
20	NVIDIA RTX 4090 48GB (China-mod) nvidia · workstation · 48GB	B	534	351	190	200	22	Estimated
21	NVIDIA RTX 6000 Ada Generation nvidia · workstation · 48GB	B	529	334	190	200	31	Estimated
22	NVIDIA GeForce RTX 4090 nvidia · enthusiast · 24GB	B	520	351	170	200	22	Estimated
23	NVIDIA GeForce RTX 3090 Ti nvidia · enthusiast · 24GB	B	520	351	170	200	22	Estimated
24	NVIDIA GeForce RTX 5090 Mobile nvidia · enthusiast · 24GB	B	517	312	170	200	57	Estimated
25	Apple Mac Studio (M3 Ultra) apple · enthusiast	B	509	333	190	170	34	Estimated
26	Apple M1 Ultra apple · enthusiast	B	507	325	200	170	30	Estimated
27	Apple M2 Ultra apple · enthusiast	B	507	325	200	170	30	Estimated
28	Apple M3 Ultra apple · enthusiast	B	506	333	190	170	30	Estimated
29	NVIDIA GeForce RTX 3090 nvidia · enthusiast · 24GB	B	505	326	170	200	26	Estimated
30	NVIDIA L40 nvidia · workstation · 48GB	B	503	301	190	200	28	Estimated
31	NVIDIA L40S nvidia · workstation · 48GB	B	500	301	190	200	24	Estimated
32	NVIDIA GeForce RTX 5080 nvidia · enthusiast · 16GB	C	490	334	140	200	26	Estimated
33	NVIDIA GeForce RTX 5070 Ti nvidia · high · 16GB	C	477	312	140	200	29	Estimated
34	NVIDIA RTX A6000 (Ampere) nvidia · workstation · 48GB	C	477	267	190	200	25	Estimated
35	NVIDIA RTX A5000 nvidia · workstation · 24GB	C	468	267	170	200	32	Estimated
36	NVIDIA A40 nvidia · workstation · 48GB	C	458	242	190	200	22	Estimated
37	NVIDIA GeForce RTX 3080 12GB nvidia · high · 12GB	C	456	317	110	200	25	Estimated
38	NVIDIA GeForce RTX 3080 Ti nvidia · enthusiast · 12GB	C	456	317	110	200	25	Estimated
39	MacBook Pro 16" M4 Max apple · enthusiast	C	445	222	200	170	44	Estimated
40	Apple M4 Max apple · enthusiast	C	435	222	200	170	30	Estimated
41	NVIDIA GeForce RTX 4080 Super nvidia · high · 16GB	C	433	256	140	200	22	Estimated
42	NVIDIA GeForce RTX 4080 nvidia · high · 16GB	C	428	249	140	200	22	Estimated
43	AMD Radeon RX 7900 XTX amd · enthusiast · 24GB	C	420	278	170	130	22	Estimated
44	NVIDIA GeForce RTX 4070 Ti Super nvidia · high · 16GB	C	418	234	140	200	23	Estimated
45	NVIDIA RTX 5000 Ada Generation nvidia · workstation · 32GB	C	414	200	170	200	22	Estimated
46	NVIDIA RTX 2080 Ti 22GB (China-mod) nvidia · mid · 22GB	C	405	214	140	200	24	Estimated
47	NVIDIA GeForce RTX 5070 nvidia · mid · 12GB	C	399	234	110	200	26	Estimated
48	NVIDIA GeForce RTX 3080 10GB nvidia · high · 10GB	C	397	264	80	200	23	Estimated
49	Apple M2 Max apple · high	C	386	162	190	170	30	Estimated
50	Apple M3 Max apple · enthusiast	C	386	162	190	170	30	Estimated
51	NVIDIA GeForce RTX 3080 16GB (Mobile) nvidia · high · 16GB	C	384	178	140	200	30	Estimated
52	Apple M1 Max apple · high	C	372	162	170	170	30	Estimated
53	AMD Radeon RX 7900 XT amd · enthusiast · 20GB	C	365	232	140	130	20	Estimated
54	NVIDIA GeForce RTX 5060 Ti 16GB nvidia · mid · 16GB	C	364	156	140	200	24	Estimated
55	NVIDIA GeForce RTX 2080 Ti nvidia · enthusiast · 11GB	C	363	214	80	200	24	Estimated
56	NVIDIA L4 nvidia · workstation · 24GB	C	360	104	170	200	40	Estimated
57	NVIDIA GeForce RTX 3070 Ti nvidia · high · 8GB	C	358	212	80	200	20	Estimated
58	NVIDIA GeForce RTX 4070 nvidia · mid · 12GB	C	356	175	110	200	24	Estimated
59	NVIDIA GeForce RTX 4070 Super nvidia · mid · 12GB	C	355	175	110	200	22	Estimated
60	NVIDIA GeForce RTX 4070 Ti nvidia · high · 12GB	C	351	175	110	200	17	Estimated
61	Apple M4 Pro apple · high	C	337	111	170	170	30	Estimated
62	AMD Radeon RX 9070 amd · high · 16GB	C	335	186	140	130	23	Estimated
63	AMD Radeon RX 9070 XT amd · high · 16GB	C	331	186	140	130	17	Estimated
64	NVIDIA GeForce RTX 2080 Super nvidia · high · 8GB	C	330	173	80	200	19	Estimated
65	AMD Radeon RX 7800 XT amd · high · 16GB	C	329	181	140	130	19	Estimated
66	NVIDIA GeForce GTX 1080 Ti nvidia · high · 11GB	C	327	168	80	200	19	Estimated
67	NVIDIA GeForce RTX 5060 nvidia · entry · 8GB	C	326	156	80	200	30	Estimated
68	NVIDIA GeForce RTX 2060 Super nvidia · mid · 8GB	C	323	156	80	200	25	Estimated
69	NVIDIA GeForce RTX 2070 nvidia · high · 8GB	C	323	156	80	200	25	Estimated
70	NVIDIA GeForce RTX 5060 Ti 8GB nvidia · mid · 8GB	C	322	156	80	200	24	Estimated
71	NVIDIA GeForce RTX 3060 Ti nvidia · high · 8GB	C	321	156	80	200	22	Estimated
72	NVIDIA GeForce RTX 4060 Ti 16GB nvidia · mid · 16GB	C	320	100	140	200	17	Estimated
73	NVIDIA GeForce RTX 2070 Super nvidia · high · 8GB	C	319	156	80	200	20	Estimated
74	NVIDIA GeForce RTX 3060 12GB nvidia · mid · 12GB	C	319	125	110	200	20	Estimated
75	NVIDIA GeForce RTX 3070 nvidia · mid · 8GB	C	319	156	80	200	20	Estimated
76	AMD Radeon RX 7900 GRE amd · high · 16GB	C	319	167	140	130	18	Estimated
77	AMD Radeon RX 6950 XT amd · enthusiast · 16GB	C	316	167	140	130	14	Estimated
78	AMD Radeon RX 6800 amd · high · 16GB	C	304	148	140	130	16	Estimated
79	AMD Ryzen AI Max+ 395 (Strix Halo) amd · workstation	C	302	74	190	130	37	Estimated
80	AMD Radeon RX 6800 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
81	AMD Radeon RX 6900 XT amd · enthusiast · 16GB	C	302	148	140	130	14	Estimated
82	NVIDIA GeForce GTX 1080 nvidia · mid · 8GB	D	286	111	80	200	17	Estimated
83	NVIDIA B200 nvidia · workstation · 180GB	D	280	0	200	200	0	Estimated
84	NVIDIA GB200 NVL72 nvidia · workstation · 13400GB	D	280	0	200	200	0	Estimated
85	NVIDIA GeForce RTX 4060 nvidia · entry · 8GB	D	279	95	80	200	23	Estimated
86	NVIDIA GeForce RTX 4060 Ti 8GB nvidia · mid · 8GB	D	278	100	80	200	17	Estimated
87	NVIDIA GeForce GTX 1070 nvidia · mid · 8GB	D	270	89	80	200	16	Estimated
88	NVIDIA GeForce GTX 1070 Ti nvidia · mid · 8GB	D	268	89	80	200	14	Estimated
89	AMD Radeon RX 7700 XT amd · mid · 12GB	D	265	125	110	130	14	Estimated
90	AMD Radeon RX 9060 XT amd · mid · 16GB	D	265	93	140	130	16	Estimated
91	NVIDIA GeForce RTX 3050 nvidia · entry · 8GB	D	263	78	80	200	17	Estimated
92	AMD Ryzen AI 9 HX 370 (Strix Point) amd · pc-npu	D	262	37	170	130	37	Estimated
93	NVIDIA GeForce GTX 1660 Super nvidia · mid · 6GB	D	261	117	30	200	26	Estimated
94	ASUS ROG Strix Scar 18 (RTX 5090 Mobile) nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
95	Razer Blade 16 (2025, RTX 5090 Mobile) nvidia · enthusiast · 24GB	D	259	0	170	200	0	Estimated
96	NVIDIA GeForce RTX 2060 nvidia · mid · 6GB	D	257	117	30	200	20	Estimated
97	Intel Arc A770 16GB intel · mid · 16GB	D	256	130	140	80	16	Estimated
98	AMD Radeon RX 7600 XT amd · mid · 16GB	D	256	84	140	130	12	Estimated
99	NVIDIA GeForce GTX 1660 Ti nvidia · mid · 6GB	D	247	100	30	200	23	Estimated
100	NVIDIA GeForce RTX 4090 Mobile nvidia · enthusiast · 16GB	D	238	0	140	200	0	Estimated
101	Intel Core Ultra 7 258V (Lunar Lake) intel · pc-npu	D	233	32	170	80	51	Estimated
102	AMD Radeon RX 6750 XT amd · high · 12GB	D	230	125	110	80	14	Estimated
103	NVIDIA GeForce RTX 3050 Ti (Mobile) nvidia · mobile · 4GB	D	224	67	30	200	23	Estimated
104	NVIDIA GeForce GTX 1650 Super nvidia · entry · 4GB	D	221	67	30	200	18	Estimated
105	AMD Radeon RX 6700 XT amd · high · 12GB	D	220	111	110	80	13	Estimated
106	NVIDIA GeForce GTX 1060 3GB nvidia · entry · 3GB	D	218	67	30	200	15	Estimated
107	Qualcomm Snapdragon 8 Elite qualcomm · mobile	D	218	21	110	80	100	Estimated
108	NVIDIA GeForce GTX 1060 6GB nvidia · entry · 6GB	D	218	67	30	200	15	Estimated
109	NVIDIA GeForce GTX 1660 nvidia · mid · 6GB	D	218	67	30	200	15	Estimated
110	Intel Arc B580 intel · mid · 12GB	D	218	106	110	80	15	Estimated
111	NVIDIA DGX Spark (Project Digits) nvidia · workstation	D	214	95	0	200	11	Estimated
112	AMD Radeon RX 5700 XT amd · high · 8GB	D	214	130	80	80	16	Estimated
113	NVIDIA GeForce GTX 1650 nvidia · entry · 4GB	D	204	45	30	200	16	Estimated
114	NVIDIA GeForce GTX 1050 Ti nvidia · entry · 4GB	D	198	39	30	200	14	Estimated
115	Apple M4 (iPad Pro) apple · mobile	D	195	49	30	170	30	Estimated
116	Qualcomm Snapdragon 8 Gen 3 qualcomm · mobile	D	193	18	80	80	98	Estimated
117	Intel Arc B570 intel · mid · 10GB	D	185	88	80	80	16	Estimated
118	Apple A18 Pro apple · mobile	D	178	24	30	170	30	Estimated
119	AMD Radeon RX 6650 XT amd · mid · 8GB	D	177	81	80	80	12	Estimated
120	Apple A17 Pro apple · mobile	D	176	21	30	170	30	Estimated
121	AMD Radeon RX 6600 XT amd · mid · 8GB	D	173	74	80	80	13	Estimated
122	AMD Radeon RX 580 8GB amd · mid · 8GB	D	172	74	80	80	11	Estimated
123	AMD Radeon RX 5500 XT 8GB amd · entry · 8GB	D	167	65	80	80	14	Estimated
124	AMD Radeon RX 6600 amd · mid · 8GB	D	167	65	80	80	14	Estimated
125	AMD Radeon RX 5600 XT amd · mid · 6GB	D	158	97	30	80	18	Estimated
126	AMD Radeon 880M (Strix Point iGPU) amd · entry	D	143	37	0	130	37	Estimated
127	AMD Radeon 780M (Phoenix iGPU) amd · entry	D	139	35	0	130	34	Estimated
128	AMD Radeon RX 570 amd · entry · 4GB	D	131	65	30	80	12	Estimated
129	Google Tensor G4 google · mobile	D	119	0	80	60	30	Estimated
130	Intel Arc 140V (Lunar Lake iGPU) intel · entry	D	115	32	0	80	52	Estimated
131	Framework Laptop 16 (RX 7700S) amd · mid · 8GB	D	112	0	80	80	0	Estimated
132	Qualcomm Snapdragon X Elite qualcomm · high	D	104	31	0	80	38	Estimated
133	Qualcomm Snapdragon X Plus qualcomm · mid	D	104	31	0	80	38	Estimated

BLK · BUY · AMAZON

Top-scoring GPUs in this table, on Amazon:NVIDIA H100 NVLNVIDIA H200 NVL (PCIe)NVIDIA H200NVIDIA H100 PCIeNVIDIA A100 80GB SXMNVIDIA H100 SXMNVIDIA RTX PRO 6000 BlackwellNVIDIA A100 40GBNVIDIA RTX PRO 5000 Blackwell 48GBNVIDIA GeForce RTX 5090

Amazon links — we may earn a small commission at no extra cost to you. Prices change; check the listing before you buy. 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