{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","arxiv_id":"2408.01800","date":"2024-08-03","proceeding":null,"authors":["Yuan YAO","Tianyu Yu","Ao Zhang","Chongyi Wang","Junbo Cui","Hongji Zhu","Tianchi Cai","Haoyu Li","Weilin Zhao","Zhihui He","Qianyu Chen","Huarong Zhou","Zhensheng Zou","Haoye Zhang","Shengding Hu","Zhi Zheng","Jie zhou","Jie Cai","Xu Han","Guoyang Zeng","Dahai Li","Zhiyuan Liu","Maosong Sun"],"abstract":"The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong OCR capability and 1.8M pixel high-resolution image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future.","url_abs":"https://arxiv.org/abs/2408.01800v1","url_pdf":"https://arxiv.org/pdf/2408.01800v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"2408-01800","repo_url":"https://github.com/OpenBMB/MiniCPM-o","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"2408-01800","repo_url":"https://github.com/openbmb/minicpm-v","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"temporal-relation-extraction","task_name":"Temporal Relation Extraction"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-relation-extraction-on-vinoground","task":"Temporal Relation Extraction","dataset":"Vinoground","model":"MiniCPM-2.6","rank_in_archive_order":11,"of":24,"metrics":{"Group Score":"11.2","Text Score":"32.6","Video Score":"29.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme-1","task":"Zero-Shot Video Question Answer","dataset":"Video-MME","model":"MiniCPM-V 2.6 (8B)","rank_in_archive_order":8,"of":11,"metrics":{"Accuracy (%)":"63.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01800"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OpenBMB/MiniCPM-o","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openbmb/minicpm-v","reach":null}],"summary":{"ran":5,"ran_draft_wrong":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":12,"ran":7,"repositories":1},"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0f35574f9b09041b","entry":"collect_chunks","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"web_demos/minicpm-o_2.6/vad_utils.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/web_demos/minicpm-o_2.6/vad_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f35574f9b09041b"}},{"code_sha256_prefix":"f067ba49686d26ba","entry":"expand_question_into_multimodal","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"chat.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/chat.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f067ba49686d26ba"}},{"code_sha256_prefix":"77e8a3ac46f3afec","entry":"get_2d_sincos_pos_embed","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"omnilmm/model/resampler.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/omnilmm/model/resampler.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77e8a3ac46f3afec"}},{"code_sha256_prefix":"50c4398a8645438a","entry":"get_abs_pos","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"omnilmm/model/resampler.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/omnilmm/model/resampler.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"code_sha256_prefix":"68b3160674a64aba","entry":"get_file_extension","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68b3160674a64aba"}},{"code_sha256_prefix":"1a3baf406bc7de64","entry":"get_parameter_number","repo":"openbmb/minicpm-v","repo_kind":"listed","path":"finetune/finetune.py","file_url":"https://github.com/openbmb/minicpm-v/blob/HEAD/finetune/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a3baf406bc7de64"}},{"code_sha256_prefix":"96d7e1c6bf4c29ec","entry":"is_image","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96d7e1c6bf4c29ec"}},{"code_sha256_prefix":"fa9adb328f246208","entry":"is_video","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa9adb328f246208"}},{"code_sha256_prefix":"2a1ffa5243150412","entry":"upload_img","repo":"openbmb/minicpm-v","repo_kind":"listed","path":"web_demos/web_demo.py","file_url":"https://github.com/openbmb/minicpm-v/blob/HEAD/web_demos/web_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a1ffa5243150412"}},{"code_sha256_prefix":"a32cd6f57d6772ae","entry":"conversation_to_ids","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"finetune/dataset.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/finetune/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a32cd6f57d6772ae"}},{"code_sha256_prefix":"d6c1484ab50b4e26","entry":"conversation_to_ids_minicpm","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"finetune/dataset.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/finetune/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6c1484ab50b4e26"}},{"code_sha256_prefix":"4212780bf7da9ddd","entry":"data_collator","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"finetune/dataset.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/finetune/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4212780bf7da9ddd"}},{"code_sha256_prefix":"2884deadbb637c3e","entry":"get_2d_sincos_pos_embed_from_grid","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"omnilmm/model/resampler.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/omnilmm/model/resampler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2884deadbb637c3e"}},{"code_sha256_prefix":"a3a415371d24af80","entry":"get_speech_timestamps","repo":"OpenBMB/MiniCPM-o","repo_kind":"official","path":"web_demos/minicpm-o_2.6/vad_utils.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/web_demos/minicpm-o_2.6/vad_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3a415371d24af80"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}