|
4 | 4 |
|
5 | 5 | ## Full list of benchmarked models |
6 | 6 |
|
| 7 | + |
7 | 8 | | Model | Amazon EC2 | Amazon SageMaker | Amazon Bedrock | |
8 | 9 | |:--------------------------------|:-------------------------------|:-------------------------------------------|:-----------------------------------| |
| 10 | +| **Deepseek-R1 distilled** | g6e | g6e | | |
| 11 | +| **Llama3.3-70b instruct** | | | On-demand | |
| 12 | +| **Qwen2.5-72b** | g5, g6e | | | |
9 | 13 | | **Amazon Nova** | | | On-demand | |
10 | 14 | | **Anthropic Claude-3 Sonnet** | | | On-demand, provisioned | |
11 | 15 | | **Anthropic Claude-3 Haiku** | | | On-demand | |
|
16 | 20 | | **Llama3.2-3b instruct** | g5 | | | |
17 | 21 | | **Llama3.1-8b instruct** | g5, p4d, p4de, p5, p5e, g6e, g6, inf2, trn1 | g4dn, g5, p3, inf2, trn1 | On-demand | |
18 | 22 | | **Llama3.1-70b instruct** | p4d, p4de, p5, p5e, g6e, g5, inf2, trn1 | inf2, trn1 | On-demand | |
19 | | -| **Llama3-8b instruct** | g5, g6e, inf2, trn1 | g4dn, g5, p3, inf2, trn1, p4d, p5e | On-demand | |
| 23 | +| **Llama3-8b instruct** | g5, g6e, inf2, trn1, c8g | g4dn, g5, p3, inf2, trn1, p4d, p5e | On-demand | |
20 | 24 | | **Llama3-70b instruct** | g5 | g4dn, g5, p3, inf2, trn1, p4d | On-demand | |
21 | 25 | | **Llama2-13b chat** | | g4dn, g5, p3, inf2, trn1, p4d | On-demand | |
22 | 26 | | **Llama2-70b chat** | | g4dn, g5, p3, inf2, trn1, p4d | On-demand | |
| 27 | +| **NousResearch-Hermes-70b** | | g5, inf2, trn1 | On-demand | |
23 | 28 | | **Amazon Titan text lite** | | | On-demand | |
24 | 29 | | **Amazon Titan text express** | | | On-demand | |
25 | 30 | | **Cohere Command text** | | | On-demand | |
|
28 | 33 | | **AI21 J2 Ultra** | | | On-demand | |
29 | 34 | | **Gemma-2b** | | g4dn, g5, p3 | | |
30 | 35 | | **Phi-3-mini-4k-instruct** | | g4dn, g5, p3 | | |
31 | | -| **distilbert-base-uncased** | | g4dn, g5, p3 | | |
| 36 | +| **distilbert-base-uncased** | | g4dn, g5, p3 | | |
0 commit comments