Title: Gemma 4 31B IT %E2%80%94 gemma-4-31b-it Canonical: https://llmeu.com/mt/models/gemma-4-31b-it/ Markdown mirror: https://llmeu.com/mt/models/gemma-4-31b-it.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json Provider: Google DeepMind Licence: apache-2.0 Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet Sources: https://huggingface.co/google/gemma-4-31B-it https://ai.google.dev/gemma/docs/gemma_4_license # Gemma 4 31B IT [Google DeepMind](/mt/providers/google/) 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 Gemma 4 31B (gemma-4-31b-it) huwa l-akbar mudell Gemma 4 irfinat bl-istruzzjonijiet, bi 31.3B parametru ta%C4%A7t Apache-2.0. Jie%C4%A7u test u imma%C4%A1ini fuq tieqa ta' kuntest ta' 256K token, u l-karta tirrapporta 85.2% fuq MMLU Pro, 84.3% fuq GPQA Diamond u 88.4% fuq MMMLU, kollha rrappurtati mill-bejjieg%C4%A7; li sservih f'BF16 te%C4%A7tie%C4%A1 a%C4%8B%C4%8Beleratur b'memorja kbira. ## Spe%C4%8Bifikazzjonijiet - Fornitur Google DeepMind (US) - Tieqa tal-kuntest 262k - Parametri 31.27B - Modalitajiet text, vision - Li%C4%8Benzja apache-2.0 %C2%B7 [licence](https://ai.google.dev/gemma/docs/gemma_4_license) - Pi%C5%BCijiet miftu%C4%A7a yes - Data tar-rilaxx 11 Mar 2026 - Kompiti [Vi%C5%BCjoni](/mt/tasks/vision/), [Ra%C4%A1unament](/mt/tasks/reasoning/), [Appo%C4%A1%C4%A1 multilingwi](/mt/tasks/multilingual-support/), [Ikkodifikar](/mt/tasks/coding/), [Sommarizzazzjoni](/mt/tasks/summarization/) ## Lingwi **Qawwi:** en, de, fr, es, it, pt **Adekwat:** nl, pl, sv, cs, ro, el, uk, ru, ar, hi, zh, ja, ko, tr #### Qawwi - en - de - fr - es - it - pt #### Adekwat - nl - pl - sv - cs - ro - el - uk - ru - ar - hi - zh - ja - ko - tr 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 - Apache-2.0 licence, unlike earlier Gemma generations - 256K-token context window - text and image input with variable resolution - vendor reports multilingual coverage in over 140 languages #### Limiti - all published scores are self-reported by the vendor - 31B parameters need a large-memory accelerator at BF16 - no evaluation has been run by LLM EU ## Mistoqsijiet frequenti ### Is Gemma 4 31B IT 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 Gemma 4 31B IT released? Gemma 4 31B IT is recorded under apache-2.0. The recorded licence text is https://ai.google.dev/gemma/docs/gemma_4_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 Gemma 4 31B IT, and what context window does it have? Gemma 4 31B IT is recorded at 31.3B (safetensors total 31,273,088,876) (source: https://huggingface.co/api/models/google/gemma-4-31B-it), with a context window of 262144 tokens (source: https://huggingface.co/google/gemma-4-31B-it). ### 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/google/gemma-4-31B-it) ### 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":"gemma-4-31b-it","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 - MMLU Pro: **85.2% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-31B-it) - GPQA Diamond: **84.3% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-31B-it) - AIME 2026, no tools: **89.2% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-31B-it) - LiveCodeBench v6: **80.0% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-31B-it) - MMMLU (multilingual MMLU): **88.4% (vendor-reported)** [source](https://huggingface.co/google/gemma-4-31B-it) ### Sorsi - [huggingface.co](https://huggingface.co/google/gemma-4-31B-it) - [ai.google.dev](https://ai.google.dev/gemma/docs/gemma_4_license) ### Re%C4%A1istru tal-bidliet tal-karta - 11 Mar 2026 %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 ### Kompiti - [Vi%C5%BCjoni](/mt/tasks/vision/) - [Sommarizzazzjoni](/mt/tasks/summarization/)