meta/llama/llama-4-scout-17b-16e
وردەکاریی سەرچاوە
وەشانی سەرچاوە: 15fb562bcf144f0415ac8dbc9c7aee1e174d2e826178c9691256acdb94156442
Meta · دەق
مۆدێلەکانی Meta Llama: وەشانەکان، تایبەتمەندییەکان، پێداویستییەکانی GPU و میوانداری
Meta Llama provides widely adopted open-weight generations; Scout and Maverick are sibling Llama 4 variants rather than sequential generations.
پوختە و مێژوو
Meta Llama is an official Meta model family represented here through independently verified release, خاڵی وەشان, license, ژینگەی جێبەجێکردن and hardware evidence. Meta Llama provides widely adopted open-weight generations; Scout and Maverick are sibling Llama 4 variants rather than sequential generations. Current public releases are grouped by the General tracks so sibling sizes and specialist branches are not presented as false chronological generations.
FusionPointAI currently tracks 3 certified public Meta Llama releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.
Broad ecosystem
Multimodal Llama 4 variants
Mature deployment tooling
تەلارسازی و مەودای مۆدێل
The verified public range spans 109B to 405B total parameters and context windows up to 10,000,000 تۆکنەکان. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.
وەشانە بڵاوکراوەکان3
ڕێڕەوەکانی مۆدێل1
نەوەی ئێستاLlama 4 Scout 17B-16E
دوا جار پشتڕاستکراوەتەوە2026-08-26T00:00:00.000000Z
نەوەکان، ڕێڕەوەکان و جۆرەکان
گشتی
Llama 3.1
بەرهەمهێنانی نوێLlama 4
بەرهەمهێنانی ئێستا 2 وەشانی هاوشێوەژینگەی جێبەجێکردن
Choose a specific Meta Llama release and certified خاڵی وەشان before sizing hardware. FusionPointAI rejects unknown ژینگەی جێبەجێکردن configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.
Validate the exact خاڵی وەشان license, ژینگەی جێبەجێکردن version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.
بەکارهێنانە باوەکان
General assistants
Private ڕێکخستنی وردی مۆدێل
Multimodal applications
پوختەی مۆڵەت
Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.
Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.
ڕێڕەوی کاتیی وەشان
meta/llama/llama-4-maverick-17b-128e
وردەکاریی سەرچاوە
وەشانی سەرچاوە: 0b389dbe619938c2b9ee945f693f2816c90ed1c6f2754c113b652873e163735f
meta/llama/llama-3-1-405b
وردەکاریی سەرچاوە
وەشانی سەرچاوە: ec5a654d6f9ae0f8c3e0ad5cf9d102d9937c302c51a497a7ae316cdb15dfed83
پرسیارە باوەکان
Which Meta Llama release is current?
Current releases are Llama 4 Scout 17B-16E, Llama 4 Maverick 17B-128E, evaluated within their respective tracks.
Can Meta Llama be self-hosted?
Only releases with a verified official خاڵی وەشان and supported ژینگەی جێبەجێکردن configuration are presented as deployable.
Which GPU should run Meta Llama?
GPU selection depends on the exact variant, خاڵی وەشان precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.
سەرچاوە فەرمییەکان
دوا جار پشتڕاستکراوەتەوە: 2026-08-26