| A | B | C | D | E | F | G | H | I | J | |
|---|---|---|---|---|---|---|---|---|---|---|
1 | Device | Engine | Model Name | Model Size | Quantization | Batch Size | Prefill (tps) | Decode (tps) | Input Seq Length | Output Seq Len |
2 | NVIDIA DGX Spark | ollama | gpt-oss | 20b | mxfp4 | 1 | 2,053.98 | 60.91 | ||
3 | NVIDIA DGX Spark | ollama | gpt-oss | 120b | mxfp4 | 1 | 94.67 | 41.88 | ||
4 | NVIDIA DGX Spark | ollama | llama-3.1 | 8b | q4_K_M | 1 | 23,169.59 | 43.18 | ||
5 | NVIDIA DGX Spark | ollama | llama-3.1 | 8b | q8_0 | 1 | 19,826.27 | 28.54 | ||
6 | NVIDIA DGX Spark | ollama | llama-3.1 | 70b | q4_K_M | 1 | 411.41 | 4.58 | ||
7 | NVIDIA DGX Spark | ollama | gemma-3 | 12b | q4_K_M | 1 | 1,513.60 | 26.51 | ||
8 | NVIDIA DGX Spark | ollama | gemma-3 | 12b | q8_0 | 1 | 1,131.42 | 16.09 | ||
9 | NVIDIA DGX Spark | ollama | gemma-3 | 27b | q4_K_M | 1 | 680.68 | 11.51 | ||
10 | NVIDIA DGX Spark | ollama | gemma-3 | 27b | q8_0 | 1 | 65.37 | 7.35 | ||
11 | NVIDIA DGX Spark | ollama | deepseek-r1 | 14b | q4_K_M | 1 | 2,500.24 | 21.45 | ||
12 | NVIDIA DGX Spark | ollama | deepseek-r1 | 14b | q8_0 | 1 | 1,816.97 | 13.68 | ||
13 | NVIDIA DGX Spark | ollama | qwen-3 | 32b | q4_K_M | 1 | 100.42 | 9.53 | ||
14 | NVIDIA DGX Spark | ollama | qwen-3 | 32b | q8_0 | 1 | 37.85 | 6.24 | ||
15 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 1 | 433.91 | 69.56 | 2048 | 2048 |
16 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 1 | 676.22 | 50.54 | 2048 | 2048 |
17 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 1 | 7,991.11 | 20.52 | 2048 | 2048 |
18 | NVIDIA DGX Spark | sglang | llama-3.1 | 70b | fp8 | 1 | 803.54 | 2.66 | 2048 | 2048 |
19 | NVIDIA DGX Spark | sglang | gemma-3 | 12b | fp8 | 1 | 1,295.83 | 6.84 | 2048 | 2048 |
20 | NVIDIA DGX Spark | sglang | gemma-3 | 27b | fp8 | 1 | 717.36 | 3.83 | 2048 | 2048 |
21 | NVIDIA DGX Spark | sglang | deepseek-r1 | 14b | fp8 | 1 | 2,177.04 | 12.02 | 2048 | 2048 |
22 | NVIDIA DGX Spark | sglang | qwen-3 | 32b | fp8 | 1 | 1,145.66 | 6.08 | 2048 | 2048 |
23 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 2 | 427.26 | 97.66 | 2048 | 2048 |
24 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 2 | 242.66 | 68.15 | 2048 | 2048 |
25 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 2 | 7,377.34 | 42.30 | 2048 | 2048 |
26 | NVIDIA DGX Spark | sglang | llama-3.1 | 70b | fp8 | 2 | 876.90 | 5.31 | 2048 | 2048 |
27 | NVIDIA DGX Spark | sglang | gemma-3 | 12b | fp8 | 2 | 1,541.21 | 16.13 | 2048 | 2048 |
28 | NVIDIA DGX Spark | sglang | gemma-3 | 27b | fp8 | 2 | 723.61 | 7.76 | 2048 | 2048 |
29 | NVIDIA DGX Spark | sglang | deepseek-r1 | 14b | fp8 | 2 | 2,027.24 | 24.00 | 2048 | 2048 |
30 | NVIDIA DGX Spark | sglang | qwen-3 | 32b | fp8 | 2 | 1,150.12 | 12.17 | 2048 | 2048 |
31 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 4 | 469.98 | 158.64 | 2048 | 2048 |
32 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 4 | 293.93 | 91.95 | 2048 | 2048 |
33 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 4 | 7,902.03 | 77.31 | 2048 | 2048 |
34 | NVIDIA DGX Spark | sglang | llama-3.1 | 70b | fp8 | 4 | 948.18 | 10.40 | 2048 | 2048 |
35 | NVIDIA DGX Spark | sglang | gemma-3 | 12b | fp8 | 4 | 1,351.51 | 30.92 | 2048 | 2048 |
36 | NVIDIA DGX Spark | sglang | gemma-3 | 27b | fp8 | 4 | 801.56 | 14.95 | 2048 | 2048 |
37 | NVIDIA DGX Spark | sglang | deepseek-r1 | 14b | fp8 | 4 | 2,106.97 | 45.28 | 2048 | 2048 |
38 | NVIDIA DGX Spark | sglang | qwen-3 | 32b | fp8 | 4 | 1,148.81 | 23.72 | 2048 | 2048 |
39 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 8 | 552.53 | 219.25 | 2048 | 2048 |
40 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 8 | 302.10 | 117.06 | 2048 | 2048 |
41 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 8 | 7,744.30 | 143.92 | 2048 | 2048 |
42 | NVIDIA DGX Spark | sglang | llama-3.1 | 70b | fp8 | 8 | 948.52 | 20.20 | 2048 | 2048 |
43 | NVIDIA DGX Spark | sglang | gemma-3 | 12b | fp8 | 8 | 1,302.91 | 55.79 | 2048 | 2048 |
44 | NVIDIA DGX Spark | sglang | gemma-3 | 27b | fp8 | 8 | 807.33 | 27.77 | 2048 | 2048 |
45 | NVIDIA DGX Spark | sglang | deepseek-r1 | 14b | fp8 | 8 | 2,073.64 | 83.51 | 2048 | 2048 |
46 | NVIDIA DGX Spark | sglang | qwen-3 | 32b | fp8 | 8 | 1,149.34 | 44.55 | 2048 | 2048 |
47 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 16 | 553.80 | 343.25 | 2048 | 2048 |
48 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 16 | 316.81 | 147.90 | 2048 | 2048 |
49 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 16 | 7,486.30 | 244.74 | 2048 | 2048 |
50 | NVIDIA DGX Spark | sglang | gemma-3 | 12b | fp8 | 16 | 1,556.14 | 93.83 | 2048 | 2048 |
51 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 32 | 545.86 | 521.87 | 2048 | 2048 |
52 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 32 | 307.22 | 203.11 | 2048 | 2048 |
53 | NVIDIA DGX Spark | sglang | llama-3.1 | 8b | fp8 | 32 | 7,949.83 | 368.09 | 2048 | 2048 |
54 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 64 | 551.13 | 781.91 | 2048 | 2048 |
55 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 64 | 308.53 | 291.65 | 2048 | 2048 |
56 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 128 | 554.15 | 1,103.12 | 2048 | 2048 |
57 | NVIDIA DGX Spark | sglang | gpt-oss | 120b | mxfp4 | 128 | 310.65 | 324.62 | 2048 | 2048 |
58 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 256 | 555.13 | 1,345.93 | 2048 | 2048 |
59 | NVIDIA DGX Spark | sglang | gpt-oss | 20b | mxfp4 | 256 | 548.70 | 2,577.98 | 512 | 128 |
60 | RTX Pro 6000 Blackwell Edition | ollama | gpt-oss | 20b | mxfp4 | 1 | 10,108.05 | 215.19 | ||
61 | RTX Pro 6000 Blackwell Edition | ollama | gpt-oss | 120b | mxfp4 | 1 | 3,409.30 | 153.32 | ||
62 | RTX Pro 6000 Blackwell Edition | ollama | llama-3.1 | 8b | q4_K_M | 1 | 38,863.83 | 201.62 | ||
63 | RTX Pro 6000 Blackwell Edition | ollama | llama-3.1 | 8b | q8_0 | 1 | 40,037.01 | 143.54 | ||
64 | RTX Pro 6000 Blackwell Edition | ollama | llama-3.1 | 70b | q4_K_M | 1 | 2,298.58 | 32.12 | ||
65 | RTX Pro 6000 Blackwell Edition | ollama | gemma-3 | 12b | q4_K_M | 1 | 6,376.34 | 111.99 | ||
66 | RTX Pro 6000 Blackwell Edition | ollama | gemma-3 | 12b | q8_0 | 1 | 6,602.39 | 82.83 | ||
67 | RTX Pro 6000 Blackwell Edition | ollama | gemma-3 | 27b | q4_K_M | 1 | 3,424.27 | 63.29 | ||
68 | RTX Pro 6000 Blackwell Edition | ollama | gemma-3 | 27b | q8_0 | 1 | 3,388.73 | 43.37 | ||
69 | RTX Pro 6000 Blackwell Edition | ollama | deepseek-r1 | 14b | q4_K_M | 1 | 10,274.55 | 114.37 | ||
70 | RTX Pro 6000 Blackwell Edition | ollama | deepseek-r1 | 14b | q8_0 | 1 | 10,825.80 | 80.17 | ||
71 | RTX Pro 6000 Blackwell Edition | ollama | qwen-3 | 32b | q4_K_M | 1 | 2,914.14 | 57.15 | ||
72 | RTX Pro 6000 Blackwell Edition | ollama | qwen-3 | 32b | q8_0 | 1 | 2,841.80 | 38.35 | ||
73 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 20b | mxfp4 | 1 | 2,480.66 | 300.14 | 2048 | 2048 |
74 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 120b | mxfp4 | 1 | 948.66 | 207.96 | 2048 | 2048 |
75 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 8b | fp8 | 1 | 38,744.08 | 143.90 | 2048 | 2048 |
76 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 70b | fp8 | 1 | 4,695.87 | 20.57 | 2048 | 2048 |
77 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 12b | fp8 | 1 | 13,371.54 | 44.15 | 2048 | 2048 |
78 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 27b | fp8 | 1 | 6,416.01 | 22.62 | 2048 | 2048 |
79 | RTX Pro 6000 Blackwell Edition | sglang | deepseek-r1 | 14b | fp8 | 1 | 14,227.95 | 73.47 | 2048 | 2048 |
80 | RTX Pro 6000 Blackwell Edition | sglang | qwen-3 | 32b | fp8 | 1 | 6,807.03 | 23.40 | 2048 | 2048 |
81 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 20b | mxfp4 | 2 | 3,461.70 | 448.62 | 2048 | 2048 |
82 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 120b | mxfp4 | 2 | 1,734.89 | 302.79 | 2048 | 2048 |
83 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 8b | fp8 | 2 | 41,981.46 | 278.52 | 2048 | 2048 |
84 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 70b | fp8 | 2 | 4,597.18 | 40.47 | 2048 | 2048 |
85 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 12b | fp8 | 2 | 13,761.76 | 79.95 | 2048 | 2048 |
86 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 27b | fp8 | 2 | 6,284.59 | 43.90 | 2048 | 2048 |
87 | RTX Pro 6000 Blackwell Edition | sglang | deepseek-r1 | 14b | fp8 | 2 | 13,160.30 | 143.12 | 2048 | 2048 |
88 | RTX Pro 6000 Blackwell Edition | sglang | qwen-3 | 32b | fp8 | 2 | 6,611.57 | 57.83 | 2048 | 2048 |
89 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 20b | mxfp4 | 4 | 5,061.47 | 754.47 | 2048 | 2048 |
90 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 120b | mxfp4 | 4 | 2,842.56 | 457.36 | 2048 | 2048 |
91 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 8b | fp8 | 4 | 39,670.10 | 529.15 | 2048 | 2048 |
92 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 70b | fp8 | 4 | 4,476.15 | 79.22 | 2048 | 2048 |
93 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 12b | fp8 | 4 | 11,786.13 | 154.23 | 2048 | 2048 |
94 | RTX Pro 6000 Blackwell Edition | sglang | gemma-3 | 27b | fp8 | 4 | 5,745.16 | 84.73 | 2048 | 2048 |
95 | RTX Pro 6000 Blackwell Edition | sglang | deepseek-r1 | 14b | fp8 | 4 | 12,526.14 | 275.83 | 2048 | 2048 |
96 | RTX Pro 6000 Blackwell Edition | sglang | qwen-3 | 32b | fp8 | 4 | 6,429.48 | 121.94 | 2048 | 2048 |
97 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 20b | mxfp4 | 8 | 5,042.54 | 1,190.91 | 2048 | 2048 |
98 | RTX Pro 6000 Blackwell Edition | sglang | gpt-oss | 120b | mxfp4 | 8 | 2,816.67 | 640.14 | 2048 | 2048 |
99 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 8b | fp8 | 8 | 37,529.57 | 969.17 | 2048 | 2048 |
100 | RTX Pro 6000 Blackwell Edition | sglang | llama-3.1 | 70b | fp8 | 8 | 4,198.60 | 153.20 | 2048 | 2048 |