Title: Yi 1.5 9B Chat vs Yi 1.5 34B Chat: Parameters, License %E2%80%94 LLM EU
Canonical: https://llmeu.com/en/compare/yi-1-5-9b-chat-vs-yi-1-5-34b-chat/
Markdown mirror: https://llmeu.com/en/compare/yi-1-5-9b-chat-vs-yi-1-5-34b-chat.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# Yi 1.5 9B Chat vs Yi 1.5 34B 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.

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 9B Chat](/en/models/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 %E2%80%94 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

[Multilingual support](/en/tasks/multilingual-support/), [Summarisation](/en/tasks/summarization/)

### [Yi 1.5 34B Chat](/en/models/yi-1-5-34b-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
- instruction-tuned checkpoint with a chat template in the repository

#### Limits

- catalogue only %E2%80%94 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 34.4B parameters, self-hosting needs a high-memory accelerator

#### Tasks

[Multilingual support](/en/tasks/multilingual-support/), [Reasoning](/en/tasks/reasoning/)

**Tasks:** [Multilingual support](/en/tasks/multilingual-support/)

## Compare models

- [Aya 23 8B vs Yi 1.5 9B Chat](/en/compare/aya-23-8b-vs-yi-1-5-9b-chat/)
- [Aya Expanse 8B vs Yi 1.5 9B Chat](/en/compare/aya-expanse-8b-vs-yi-1-5-9b-chat/)
- [Command R (08-2024) vs Yi 1.5 34B Chat](/en/compare/command-r-08-2024-vs-yi-1-5-34b-chat/)
- [DeepSeek-R1-Distill-Qwen-32B vs Yi 1.5 34B Chat](/en/compare/deepseek-r1-distill-qwen-32b-vs-yi-1-5-34b-chat/)
- [Devstral Small 2 (24B) vs Yi 1.5 34B Chat](/en/compare/devstral-small-2-24b-vs-yi-1-5-34b-chat/)
- [Diffusiongemma 26B A4B It vs Yi 1.5 34B Chat](/en/compare/diffusiongemma-26b-a4b-it-vs-yi-1-5-34b-chat/)