Compare
Aya 23 8B vs Falcon 7B
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.
| Aya 23 8B | Falcon 7B | |
|---|---|---|
| Provider | Cohere | Technology Innovation Institute (TII) |
| Parameters | 8.03B | 7.2B |
| Context window | 8.2k | Not verified: the provider has not documented this claim. |
| License | cc-by-nc-4.0 | apache-2.0 |
| Modalities | text | text |
| Release date | 19 May 2024 | 24 Apr 2023 |
| Languages | Strong: en, fr, de, es, it, pt Adequate: nl, pl, cs, el, ro, ru, uk, tr, ar, he, fa, hi, id, vi, zh, ja, ko | Strong: en Adequate: — |
| Open weights | yes | yes |
| Tasks | Multilingual support, Translation, Summarisation | Multilingual support |
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
Aya 23 8B
Strengths
- 23 declared languages with a European emphasis
- appears as a baseline in an independent European-language evaluation
- small footprint for fine-tuning
Limits
- CC-BY-NC-4.0 forbids commercial serving
- 8192-token context window and dated May 2024
- superseded by Aya Expanse
Tasks
Falcon 7B
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 7.2B parameters it fits on a single accelerator
- the model page lists en
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 7.2B parameters, the weights fit on a single modest accelerator
Tasks
Tasks: Multilingual support