Title: GLM-4.7-Flash %E2%80%94 glm-4-7-flash Canonical: https://llmeu.com/sv/models/glm-4-7-flash/ Markdown mirror: https://llmeu.com/sv/models/glm-4-7-flash.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json Provider: Z.ai (Zhipu AI) Licence: mit Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet Sources: https://huggingface.co/zai-org/GLM-4.7-Flash https://z.ai/blog/glm-4.7 # GLM-4.7-Flash [Z.ai (Zhipu AI)](/sv/providers/zai-org/) Senast granskad: 14 okt. 2026 ## Suver%C3%A4nitet och hosting Den h%C3%A4r modellen finns i katalogen f%C3%B6r referens. Den finns %C3%A4nnu inte hos LLM EU, och ingen f%C3%B6rstaparts%C3%A4ndpunkt betj%C3%A4nar den h%C3%A4r. Beg%C3%A4randen till den g%C3%A5r direkt till leverant%C3%B6ren, enligt leverant%C3%B6rens egna villkor. ## Sammanfattning GLM-4.7-Flash %C3%A4r en 30B-A3B mixture-of-experts-modell med 31.2B parametrar, sl%C3%A4ppt under MIT-licensen med en konfigurationsmax p%C3%A5 202 752 tokens. Modellkortet rapporterar 91.6 p%C3%A5 AIME 25 och 59.2 p%C3%A5 SWE-bench Verified, med en j%C3%A4mf%C3%B6relsetabell mot Qwen3-30B-A3B-Thinking och gpt-oss-20b. Den %C3%A4r positionerad som ett l%C3%A4ttviktsdistributionsalternativ i 30B-klassen. ## Specifikationer - Leverant%C3%B6r Z.ai (Zhipu AI) (CN) - Kontextf%C3%B6nster 203k - Parametrar 31.22B - Modaliteter text - Licens mit %C2%B7 [licence](https://opensource.org/license/mit) - %C3%96ppna vikter yes - Utgivningsdatum 19 jan. 2026 - Uppgifter [Resonemang](/sv/tasks/reasoning/), [Kodning](/sv/tasks/coding/), [L%C3%A5g kostnad](/sv/tasks/cheap/), [Sammanfattning](/sv/tasks/summarization/) ## Spr%C3%A5k **Stark:** en, zh **Tillr%C3%A4cklig:** de, fr, es, it, pt, ru, ja, ko #### Stark - en - zh #### Tillr%C3%A4cklig - de - fr - es - it - pt - ru - ja - ko Inte verifierad: leverant%C3%B6ren har inte dokumenterat detta p%C3%A5st%C3%A5ende. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists. ## N%C3%A4r den ska anv%C3%A4ndas #### Styrkor - MIT licence with a permissive commercial position - high published maths score for a 30B-class model - roughly 200K-token context window #### Begr%C3%A4nsningar - benchmark table is self-reported by the vendor - English and Chinese are the only declared languages - no evaluation has been run by LLM EU ## Vanliga fr%C3%A5gor ### Is GLM-4.7-Flash 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 GLM-4.7-Flash released? GLM-4.7-Flash is recorded under mit. The recorded licence text is https://opensource.org/license/mit. 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 GLM-4.7-Flash, and what context window does it have? GLM-4.7-Flash is recorded at 31.2B (safetensors total 31,221,488,576); a 30B-A3B mixture of experts (source: https://huggingface.co/api/models/zai-org/GLM-4.7-Flash), with a context window of 202752 tokens (source: https://huggingface.co/zai-org/GLM-4.7-Flash/blob/main/config.json). ### Priss%C3%A4ttning Den h%C3%A4r modellen finns i katalogen f%C3%B6r referens. Den finns %C3%A4nnu inte hos LLM EU, och ingen f%C3%B6rstaparts%C3%A4ndpunkt betj%C3%A4nar den h%C3%A4r. Beg%C3%A4randen till den g%C3%A5r direkt till leverant%C3%B6ren, enligt leverant%C3%B6rens egna villkor. ### Verifieringsstatus Om ett f%C3%A4lt inte har n%C3%A5gon k%C3%A4lla visar kortet det som overifierat i st%C3%A4llet f%C3%B6r att fylla i det. Ett tomt f%C3%A4lt %C3%A4r information. LLM EU Verified betyder dokumenterad, inte juridiskt certifierad. Det %C3%A4r inte en bed%C3%B6mning av %C3%B6verensst%C3%A4mmelse enligt AI-f%C3%B6rordningen och LLM EU %C3%A4r inte ett EU-organ. ### Versioner och varianter - catalogue %C2%B7 Endast katalog %C2%B7 [weights](https://huggingface.co/zai-org/GLM-4.7-Flash) ### Exempelbeg%C3%A4ran ``` curl https://api.llmeu.com/v1/chat/completions \ -H "Authorization: Bearer $LLMEU_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"glm-4-7-flash","messages":[{"role":"user","content":"Hello"}]}' ``` Ingen lekplats %C3%A4r distribuerad f%C3%B6r denna modell: ingen endpoint hanterar den, s%C3%A5 en f%C3%B6rfr%C3%A5gan skulle inte ha n%C3%A5gonstans att ta v%C3%A4gen. ### Benchmarks - AIME 25: **91.6 (vendor-reported)** [source](https://huggingface.co/zai-org/GLM-4.7-Flash) - GPQA: **75.2 (vendor-reported)** [source](https://huggingface.co/zai-org/GLM-4.7-Flash) - SWE-bench Verified: **59.2 (vendor-reported)** [source](https://huggingface.co/zai-org/GLM-4.7-Flash) - LiveCodeBench v6: **64.0 (vendor-reported)** [source](https://huggingface.co/zai-org/GLM-4.7-Flash) - %CF%84%C2%B2-Bench: **79.5 (vendor-reported)** [source](https://huggingface.co/zai-org/GLM-4.7-Flash) ### K%C3%A4llor - [huggingface.co](https://huggingface.co/zai-org/GLM-4.7-Flash) - [z.ai](https://z.ai/blog/glm-4.7) ### Kortets %C3%A4ndringslogg - 19 jan. 2026 %E2%80%94 Utgivningsdatum - 14 okt. 2026 %E2%80%94 Senast granskad Senast granskad: 14 okt. 2026 ### Uppgifter - [Kodning](/sv/tasks/coding/) - [L%C3%A5g kostnad](/sv/tasks/cheap/) - [Sammanfattning](/sv/tasks/summarization/)