ModelsLeaderboardHardwareEvalsTrainRentalsAPI Docs
Language

Hardware leaderboard

See which hardware is used by the most benchmark submitters, then drill in by hardware type.

RTX 3090

18 users · 106 runs

Best
241 tok/s
Median
40.8 tok/s
Min
5.5 tok/s
8x variant5 runs4x variant7 runs2x variant45 runs

RTX 5090

8 users · 26 runs

Best
286 tok/s
Median
121 tok/s
Min
54.6 tok/s
2x variant2 runs

GB10 Grace Blackwell

7 users · 38 runs

Best
102 tok/s
Median
30.9 tok/s
Min
4.7 tok/s

RTX PRO 6000 Blackwell

6 users · 35 runs

Best
1.0k tok/s
Median
86.2 tok/s
Min
14.7 tok/s
8x variant2 runs

RTX 4090

6 users · 16 runs

Best
214 tok/s
Median
74.2 tok/s
Min
41.8 tok/s

Ryzen AI Max 395

5 users · 174 runs

Best
107 tok/s
Median
46.1 tok/s
Min
3.8 tok/s

RX 7900 XTX

5 users · 45 runs

Best
577 tok/s
Median
94.3 tok/s
Min
1.6 tok/s

Radeon AI Pro R9700

4 users · 108 runs

Best
1.4k tok/s
Median
67.5 tok/s
Min
6.2 tok/s
3x variant93 runs2x variant10 runs

M4 Max

3 users · 13 runs

Best
135 tok/s
Median
22.0 tok/s
Min
13.0 tok/s

M5 Max

3 users · 12 runs

Best
122 tok/s
Median
53.0 tok/s
Min
17.8 tok/s

RTX 5070 Ti

3 users · 3 runs

Best
141 tok/s
Median
133 tok/s
Min
124 tok/s
2x variant1 runs

Intel Arc Pro B70

2 users · 147 runs

Best
89.3 tok/s
Median
40.3 tok/s
Min
0.5 tok/s
4x variant100 runs3x variant22 runs2x variant11 runs

RTX 3060

2 users · 47 runs

Best
161 tok/s
Median
74.0 tok/s
Min
35.0 tok/s

RTX 3080

2 users · 37 runs

Best
149 tok/s
Median
74.0 tok/s
Min
10.0 tok/s

RTX 3090 Ti

2 users · 9 runs

Best
156 tok/s
Median
119 tok/s
Min
32.6 tok/s
2x variant2 runs

Multi GPU

2 users · 4 runs

Best
34.3 tok/s
Median
30.8 tok/s
Min
24.0 tok/s
2x variant4 runs

RTX 5060 Ti

2 users · 4 runs

Best
158 tok/s
Median
85.0 tok/s
Min
32.1 tok/s
2x variant2 runs

RTX 4060 Ti

2 users · 2 runs

Best
62.0 tok/s
Median
61.1 tok/s
Min
60.2 tok/s
2x variant1 runs

GTX 1080 Ti

1 users · 26 runs

Best
94.9 tok/s
Median
30.9 tok/s
Min
2.2 tok/s

RTX A5000

1 users · 16 runs

Best
325 tok/s
Median
261 tok/s
Min
32.3 tok/s

M3 Ultra

1 users · 15 runs

Best
141 tok/s
Median
57.1 tok/s
Min
18.5 tok/s

RTX 2080

1 users · 15 runs

Best
93.0 tok/s
Median
21.0 tok/s
Min
10.0 tok/s

M5 Pro

1 users · 14 runs

Best
106 tok/s
Median
77.0 tok/s
Min
5.4 tok/s

GB10 Grace Blackwell

1 users · 12 runs

Best
94.8 tok/s
Median
27.5 tok/s
Min
11.9 tok/s
2x variant5 runs

Tesla P100

1 users · 10 runs

Best
144 tok/s
Median
41.1 tok/s
Min
7.5 tok/s
2x variant6 runs

RX 9060 XT

1 users · 9 runs

Best
100 tok/s
Median
53.9 tok/s
Min
38.1 tok/s

RX 9070 XT

1 users · 9 runs

Best
96.6 tok/s
Median
24.9 tok/s
Min
1.0 tok/s

H200 NVL

1 users · 7 runs

Best
2.7k tok/s
Median
333 tok/s
Min
175 tok/s
2x variant4 runs

H200 SXM

1 users · 7 runs

Best
878 tok/s
Median
496 tok/s
Min
197 tok/s
4x variant7 runs

Ryzen 9 7940HS Radeon 780M Minisforum UM790 Pro

1 users · 7 runs

Best
24.8 tok/s
Median
19.5 tok/s
Min
2.8 tok/s

Core Ultra Meteor Lake Ultra 7 155H

1 users · 4 runs

Best
28.0 tok/s
Median
10.3 tok/s
Min
6.5 tok/s

Intel R Core TM Ultra 7 155H

1 users · 4 runs

Best
27.6 tok/s
Median
14.0 tok/s
Min
8.4 tok/s

MT6897 TECNO POVA 7 Ultra 5G / Mali G615 MC6

1 users · 4 runs

Best
19.1 tok/s
Median
16.9 tok/s
Min
7.1 tok/s

RTX 4070

1 users · 4 runs

Best
62.1 tok/s
Median
57.4 tok/s
Min
54.5 tok/s

RTX A6000

1 users · 4 runs

Best
166 tok/s
Median
131 tok/s
Min
97.3 tok/s
2x variant4 runs

RTX 2080 Ti

1 users · 3 runs

Best
106 tok/s
Median
89.0 tok/s
Min
80.0 tok/s

RX 9070

1 users · 3 runs

Best
76.0 tok/s
Median
47.0 tok/s
Min
34.2 tok/s

Strix Halo Radeon 8060S

1 users · 3 runs

Best
256 tok/s
Median
105 tok/s
Min
88.3 tok/s

Jetson Orin Orin Nano Super Developer Kit

1 users · 2 runs

Best
27.9 tok/s
Median
21.9 tok/s
Min
15.9 tok/s

5060 Ti

1 users · 1 runs

Best
23.0 tok/s
Median
23.0 tok/s
Min
23.0 tok/s

GTX 1060

1 users · 1 runs

Best
15.0 tok/s
Median
15.0 tok/s
Min
15.0 tok/s

GTX 1650

1 users · 1 runs

Best
30.6 tok/s
Median
30.6 tok/s
Min
30.6 tok/s

M2 Pro

1 users · 1 runs

Best
33.0 tok/s
Median
33.0 tok/s
Min
33.0 tok/s

Qualcomm Snapdragon 888 ARM64

1 users · 1 runs

Best
6.2 tok/s
Median
6.2 tok/s
Min
6.2 tok/s

Radeon 8060S

1 users · 1 runs

Best
14.8 tok/s
Median
14.8 tok/s
Min
14.8 tok/s

RTX 3070 Ti

1 users · 1 runs

Best
33.5 tok/s
Median
33.5 tok/s
Min
33.5 tok/s

RTX 3080 Ti

1 users · 1 runs

Best
15.4 tok/s
Median
15.4 tok/s
Min
15.4 tok/s

RTX 4060

1 users · 1 runs

Best
29.9 tok/s
Median
29.9 tok/s
Min
29.9 tok/s

RTX 4070 Super

1 users · 1 runs

Best
77.4 tok/s
Median
77.4 tok/s
Min
77.4 tok/s

RTX 5070

1 users · 1 runs

Best
64.5 tok/s
Median
64.5 tok/s
Min
64.5 tok/s

RTX 5080

1 users · 1 runs

Best
151 tok/s
Median
151 tok/s
Min
151 tok/s

RTX PRO 6000

1 users · 1 runs

Best
92.8 tok/s
Median
92.8 tok/s
Min
92.8 tok/s
2x variant1 runs

RX 5700 XT

1 users · 1 runs

Best
61.6 tok/s
Median
61.6 tok/s
Min
61.6 tok/s

RX 6800

1 users · 1 runs

Best
89.2 tok/s
Median
89.2 tok/s
Min
89.2 tok/s

RX 6950 XT

1 users · 1 runs

Best
222 tok/s
Median
222 tok/s
Min
222 tok/s

Ryzen AI Max Max 395

1 users · 1 runs

Best
12.7 tok/s
Median
12.7 tok/s
Min
12.7 tok/s

Ryzen AI Max Radeon 780M

1 users · 1 runs

Best
26.9 tok/s
Median
26.9 tok/s
Min
26.9 tok/s

Tesla V100

1 users · 1 runs

Best
66.8 tok/s
Median
66.8 tok/s
Min
66.8 tok/s