Phi-4 is Microsoft’s compact 14B reasoning model, MIT-licensed, which punches well above
\nits size on mathematics and logic. It needs about 9 GB of VRAM at 4-bit, running comfortably
\non an RTX 4070 or RTX 3060 12GB, and costs $0.07 in \/ $0.14 out per million tokens
\nhosted.<\/p>\n
The Phi line’s whole thesis is that curated, textbook-quality training data beats raw
\nscale for reasoning tasks, and Phi-4 is the clearest evidence for it \u2014 a 14B model competing
\non maths and logic benchmarks with models several times larger. The cost of that focus is the
\n16K context window, by far the narrowest in this database and a hard limit for any workload
\ninvolving documents, long conversations or retrieval. Read it as a specialist: excellent for
\nstructured reasoning over short inputs \u2014 maths tutoring, logic and code puzzles, deterministic
\nextraction from small payloads \u2014 and the wrong tool the moment your prompt grows. If you need
\nPhi-4’s reasoning with room to work, a 128K-context model in the same hardware bracket such
\nas Qwen3 14B is the better trade.<\/p>","protected":false},"excerpt":{"rendered":"
What is Phi-4? Phi-4 is Microsoft’s compact 14B reasoning model, MIT-licensed, which punches well above its size on mathematics and […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"cm_developer":"Microsoft","cm_model_type":"LLM (dense)","cm_modality":"Text \u2192 Text","cm_parameters":"14B","cm_context_window":"16K","cm_max_output":"","cm_license":"MIT (open)","cm_open_weights":"yes","cm_release_date":"2025","cm_input_price":"0.07","cm_output_price":"0.14","cm_api_providers":"Azure, OpenRouter, Ollama","cm_vram_fp16":"","cm_vram_q4":"~9 GB","cm_min_gpu":"RTX 4070 12GB \/ RTX 3060 12GB","cm_benchmarks":"","cm_official_url":"https:\/\/huggingface.co\/microsoft"},"class_list":["post-1244","ai_model","type-ai_model","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/ai_model\/1244","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/ai_model"}],"about":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/types\/ai_model"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/media?parent=1244"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}