Compare
Yi 1.5 6B Chat vs Yi 1.5 9B Chat
Put two to four models side by side on the fields that decide a deployment: context, price, region, license, languages, hosting, and what is verified.
| Yi 1.5 6B Chat | Yi 1.5 9B Chat | |
|---|---|---|
| Provider | 01.AI | 01.AI |
| Parameters | 6.1B | 8.8B |
| Context window | Not verified: the provider has not documented this claim. | Not verified: the provider has not documented this claim. |
| License | apache-2.0 | apache-2.0 |
| Modalities | text | text |
| Release date | 11 May 2024 | 10 May 2024 |
| Languages | Not verified: the provider has not documented this claim. | Not verified: the provider has not documented this claim. |
| Open weights | yes | yes |
| Tasks | Multilingual support, Low cost, Summarisation | Multilingual support, Summarisation |
Where two models differ, this table shows the difference and stops. LLM EU publishes no winner badge without a documented score for that task, and a missing figure stays missing instead of becoming a zero.
When to use it
Yi 1.5 6B Chat
Strengths
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
- at 6.1B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
Limits
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 6.1B parameters, the weights fit on a single modest accelerator
Tasks
Yi 1.5 9B Chat
Strengths
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
- at 8.8B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
Limits
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 8.8B parameters, the weights fit on a single modest accelerator
Tasks
Tasks: Multilingual support, Summarisation