Title: Llama 4 Maverick 17 %E2%80%94 llama-4-maverick-17b-128e-instruct Canonical: https://llmeu.com/mt/models/llama-4-maverick-17b-128e-instruct/ Markdown mirror: https://llmeu.com/mt/models/llama-4-maverick-17b-128e-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: other Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet Sources: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct https://ai.meta.com/blog/llama-4-multimodal-intelligence/ https://docs.aws.eu/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html # Llama 4 Maverick 17B-128E Instruct [Meta](/mt/providers/meta/) A%C4%A7%C4%A7ar revi%C5%BCjoni: 14 Ott 2026 ## Sovranit%C3%A0 u ospitar Dan il-mudell huwa kkatalgat g%C4%A7al referenza. G%C4%A7adu mhux ospitat fuq LLM EU, u l-ebda endpoint tal-ewwel parti ma jservih hawn. It-talbiet lejh imorru direttament g%C4%A7and il-fornitur, ta%C4%A7t it-termini tal-fornitur stess. ## Sommarju Llama 4 Maverick huwa l-mudell ta' ta%C4%A7lita ta' esperti Llama 4 akbar ta' Meta: 17B parametru attiv, 128 espert u madwar 400B parametru totali, b'tieqa ta' kuntest ippubblikata ta' 1M tokens. Jie%C4%A7u test u imma%C4%A1ini u huwa po%C5%BCizzjonat g%C4%A7al xog%C4%A7ol ta' assistent %C4%A1enerali u fehim tal-imma%C4%A1ini. B%C4%A7al Scout, huwa mibg%C4%A7ut ta%C4%A7t il-Li%C4%8Benzja Komunitarja Llama 4 bil-limitu ta' 700M utent attiv fix-xahar. ## Spe%C4%8Bifikazzjonijiet - Fornitur Meta (US) - Tieqa tal-kuntest 1.0M - Parametri 401.58B - Modalitajiet text, vision - Li%C4%8Benzja other %C2%B7 [licence](https://www.llama.com/llama4/license/) - Pi%C5%BCijiet miftu%C4%A7a yes - Data tar-rilaxx 05 Apr 2025 - Kompiti [Vi%C5%BCjoni](/mt/tasks/vision/), [Ra%C4%A1unament](/mt/tasks/reasoning/), [Appo%C4%A1%C4%A1 multilingwi](/mt/tasks/multilingual-support/), [Sommarizzazzjoni](/mt/tasks/summarization/) ## Lingwi **Qawwi:** en, de, fr, es, it, pt, hi **Adekwat:** ar, id, th, tl, vi #### Qawwi - en - de - fr - es - it - pt - hi #### Adekwat - ar - id - th - tl - vi Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists. ## Meta tu%C5%BCah #### Sa%C4%A7%C4%A7iet - multimodal input with 1M-token context - 17B active parameters keep per-token compute moderate - vendor reports competitiveness with much larger dense models #### Limiti - about 400B total parameters must fit in memory even though only 17B are active - Llama 4 Community License, not an OSI licence - Meta%E2%80%99s benchmark comparisons are self-reported ## Mistoqsijiet frequenti ### Is Llama 4 Maverick 17B-128E 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 4 Maverick 17B-128E Instruct released? Llama 4 Maverick 17B-128E Instruct is recorded under other. The recorded licence text is https://www.llama.com/llama4/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 4 Maverick 17B-128E Instruct, and what context window does it have? Llama 4 Maverick 17B-128E Instruct is recorded at about 400B total, 17B active, 128 experts (safetensors total 401,583,781,376) (source: https://huggingface.co/api/models/meta-llama/Llama-4-Maverick-17B-128E-Instruct), with a context window of 1048576 tokens (source: https://docs.aws.eu/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html). ### Prezzijiet Dan il-mudell huwa kkatalgat g%C4%A7al referenza. G%C4%A7adu mhux ospitat fuq LLM EU, u l-ebda endpoint tal-ewwel parti ma jservih hawn. It-talbiet lejh imorru direttament g%C4%A7and il-fornitur, ta%C4%A7t it-termini tal-fornitur stess. ### Status ta' verifika Fejn qasam m'g%C4%A7andux sors, il-kard turih b%C4%A7ala mhux verifikat minflok ma timlih. Qasam vojt huwa informazzjoni. LLM EU Verified ifisser dokumentat, mhux i%C4%8B%C4%8Bertifikat legalment. Mhuwiex valutazzjoni ta' konformit%C3%A0 mal-AI Act u LLM EU mhuwiex korp tal-UE. ### Ver%C5%BCjonijiet u varjanti - catalogue %C2%B7 Katalgu biss %C2%B7 [weights](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct) ### E%C5%BCempju ta' talba ``` curl https://api.llmeu.com/v1/chat/completions \ -H "Authorization: Bearer $LLMEU_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"llama-4-maverick-17b-128e-instruct","messages":[{"role":"user","content":"Hello"}]}' ``` L-ebda playground mhuwiex deplojat g%C4%A7al dan il-mudell: l-ebda endpoint ma jservih, allura rikjesta ma jkollha fejn tmur. ### Benchmarks L-ebda evalwazzjoni ppubblikata. Din hija lakuna, mhux ri%C5%BCultat mo%C4%A7bi. ### Sorsi - [huggingface.co](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct) - [ai.meta.com](https://ai.meta.com/blog/llama-4-multimodal-intelligence/) - [docs.aws.eu](https://docs.aws.eu/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html) ### Re%C4%A1istru tal-bidliet tal-karta - 05 Apr 2025 %E2%80%94 Data tar-rilaxx - 14 Ott 2026 %E2%80%94 A%C4%A7%C4%A7ar revi%C5%BCjoni A%C4%A7%C4%A7ar revi%C5%BCjoni: 14 Ott 2026