Title: Llama 3.1 8B Instruct %E2%80%94 llama-3-1-8b-instruct Canonical: https://llmeu.com/hu/models/llama-3-1-8b-instruct/ Markdown mirror: https://llmeu.com/hu/models/llama-3-1-8b-instruct.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json Provider: Meta Licence: llama3.1 Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet Sources: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct https://www.llama.com/llama3_1/license/ # Llama 3.1 8B Instruct [Meta](/hu/providers/meta/) Utols%C3%B3 ellen%C5%91rz%C3%A9s: 2026. okt. 14. ## Szuverenit%C3%A1s %C3%A9s hosting Ez a modell referenciak%C3%A9nt szerepel a katal%C3%B3gusban. Az LLM EU m%C3%A9g nem %C3%BCzemelteti, %C3%A9s itt saj%C3%A1t v%C3%A9gpont nem szolg%C3%A1lja ki. A hozz%C3%A1 int%C3%A9zett k%C3%A9r%C3%A9sek k%C3%B6zvetlen%C3%BCl a szolg%C3%A1ltat%C3%B3hoz mennek, a szolg%C3%A1ltat%C3%B3 saj%C3%A1t felt%C3%A9telei szerint. ## %C3%96sszefoglal%C3%B3 A Llama 3.1 8B Instruct a Meta k%C3%B6zepes m%C3%A9ret%C5%B1 utas%C3%ADt%C3%A1sk%C3%B6vet%C5%91 modellje 128k tokenes kontextusablakkal %C3%A9s eszk%C3%B6zh%C3%ADv%C3%A1si t%C3%A1mogat%C3%A1ssal, a Llama 3.1 Community License alatt kiadva. Ez a licenc enged%C3%A9lyezi a kereskedelmi felhaszn%C3%A1l%C3%A1st, de 700 milli%C3%B3 havi akt%C3%ADv felhaszn%C3%A1l%C3%B3 felett licencet ig%C3%A9nyel a Met%C3%A1t%C3%B3l, %C3%A9s hozz%C3%A1ad egy elfogadhat%C3%B3 haszn%C3%A1lati szab%C3%A1lyzatot. Tov%C3%A1bbra is az egyik leggyakrabban let%C3%B6lt%C3%B6tt ny%C3%ADlt ellen%C5%91rz%C5%91pont %C3%A9s egy standard alapvonal; az OpenGPT-X eur%C3%B3pai nyelvi %C3%A9rt%C3%A9kel%C3%A9s%C3%A9n 0,563 pontot %C3%A9r el az EU21-en. ## Specifik%C3%A1ci%C3%B3k - Szolg%C3%A1ltat%C3%B3 Meta (US) - Kontextusablak 131k - Param%C3%A9terek 8.03B - Modalit%C3%A1sok text - Licenc llama3.1 %C2%B7 [licence](https://www.llama.com/llama3_1/license/) - Ny%C3%ADlt s%C3%BAlyok yes - Kiad%C3%A1s d%C3%A1tuma 2024. j%C3%BAl. 23. - Feladatok [Alacsony k%C3%B6lts%C3%A9g](/hu/tasks/cheap/), [Lek%C3%A9rdez%C3%A9s (RAG)](/hu/tasks/rag/), [%C3%96sszefoglal%C3%A1s](/hu/tasks/summarization/), [T%C3%B6bbnyelv%C5%B1 t%C3%A1mogat%C3%A1s](/hu/tasks/multilingual-support/), [%C3%9Cgyf%C3%A9lszolg%C3%A1lat](/hu/tasks/customer-support/) ## Nyelvek **Er%C5%91s:** en, de, fr, it, pt, es **Megfelel%C5%91:** hi, th #### Er%C5%91s - en - de - fr - it - pt - es #### Megfelel%C5%91 - hi - th Nincs ellen%C5%91rizve: a szolg%C3%A1ltat%C3%B3 nem dokument%C3%A1lta ezt az %C3%A1ll%C3%ADt%C3%A1st. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists. ## Mikor %C3%A9rdemes haszn%C3%A1lni #### Er%C5%91ss%C3%A9gek - 128k-token context window at the 8B size class - very broad tooling and quantisation support - published EU21 evaluation against European-focused models #### Korl%C3%A1tok - Llama 3.1 Community License, not an OSI licence, with a 700M MAU threshold - English-centric training data; weaker on smaller EU languages - released July 2024 and behind current 8B models ## Gyakran ism%C3%A9telt k%C3%A9rd%C3%A9sek ### Is Llama 3.1 8B Instruct served on LLM EU? It has no endpoint in the catalogue, so it is catalogue only %E2%80%94 not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment. ### Under what licence is Llama 3.1 8B Instruct released? Llama 3.1 8B Instruct is recorded under llama3.1. The recorded licence text is https://www.llama.com/llama3_1/license/. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs. ### How large is Llama 3.1 8B Instruct, and what context window does it have? Llama 3.1 8B Instruct is recorded at 8.03B (safetensors total 8,030,261,248) (source: https://huggingface.co/api/models/meta-llama/Llama-3.1-8B-Instruct), with a context window of 131072 tokens (source: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). ### %C3%81raz%C3%A1s Ez a modell referenciak%C3%A9nt szerepel a katal%C3%B3gusban. Az LLM EU m%C3%A9g nem %C3%BCzemelteti, %C3%A9s itt saj%C3%A1t v%C3%A9gpont nem szolg%C3%A1lja ki. A hozz%C3%A1 int%C3%A9zett k%C3%A9r%C3%A9sek k%C3%B6zvetlen%C3%BCl a szolg%C3%A1ltat%C3%B3hoz mennek, a szolg%C3%A1ltat%C3%B3 saj%C3%A1t felt%C3%A9telei szerint. ### Ellen%C5%91rz%C3%A9si %C3%A1llapot Ahol egy mez%C5%91nek nincs forr%C3%A1sa, a k%C3%A1rtya ellen%C5%91rizetlenk%C3%A9nt jelen%C3%ADti meg ahelyett, hogy kit%C3%B6lten%C3%A9. Az %C3%BCres mez%C5%91 is inform%C3%A1ci%C3%B3. Az LLM EU Verified dokument%C3%A1lts%C3%A1got jelent, nem jogi tan%C3%BAs%C3%ADt%C3%A1st. Ez nem az AI Act szerinti megfelel%C5%91s%C3%A9g%C3%A9rt%C3%A9kel%C3%A9s, %C3%A9s az LLM EU nem EU-s szerv. ### Verzi%C3%B3k %C3%A9s v%C3%A1ltozatok - catalogue %C2%B7 Csak katal%C3%B3gusban %C2%B7 [weights](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) ### P%C3%A9ldak%C3%A9r%C3%A9s ``` curl https://api.llmeu.com/v1/chat/completions \ -H "Authorization: Bearer $LLMEU_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"llama-3-1-8b-instruct","messages":[{"role":"user","content":"Hello"}]}' ``` Ehhez a modellhez nincs playground telep%C3%ADtve: egyetlen v%C3%A9gpont sem szolg%C3%A1lja ki, %C3%ADgy a k%C3%A9r%C3%A9snek nem lenne hov%C3%A1 mennie. ### Benchmarkok - EU21 average (translated ARC, HellaSwag, TruthfulQA, MMLU): **0.563 (OpenGPT-X evaluation)** [source](https://huggingface.co/openGPT-X/Teuken-7B-instruct-v0.6) ### Forr%C3%A1sok - [huggingface.co](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) - [www.llama.com](https://www.llama.com/llama3_1/license/) ### A k%C3%A1rtya v%C3%A1ltoz%C3%A1snapl%C3%B3ja - 2024. j%C3%BAl. 23. %E2%80%94 Kiad%C3%A1s d%C3%A1tuma - 2026. okt. 14. %E2%80%94 Utols%C3%B3 ellen%C5%91rz%C3%A9s Utols%C3%B3 ellen%C5%91rz%C3%A9s: 2026. okt. 14. ### Feladatok - [%C3%9Cgyf%C3%A9lszolg%C3%A1lat](/hu/tasks/customer-support/)