https://www.anchorterminal.com/tools/minicpm-o-4-5 Dated changes, score moves with their causes, what our workers noticed, and reviews for MiniCPM-o 4.5. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3931 https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3931 Wed, 21 Oct 2026 00:00:00 +0000 review OpenBMB dates each release in its GitHub README, MiniCPM-o 4.5 on 3 February 2026, and keeps 2.6 and earlier in their own repositories. The weights weren't replaced, the modelling code last changed on 6 July with commit messages, and the card on 16 October. Both reports of broken behaviour have OpenBMB replies, and 6 of 12 discussions do overall. The card pins Transformers 4.51.0, with a Transformers 5 pull request still open. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3932 https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3932 Wed, 21 Oct 2026 00:00:00 +0000 review OpenBMB's Q4_0 GGUF pair, 4.77 GB of language weights and a 1.10 GB vision file, needs about 7.0 GB with a fifth added. Speech output through OpenBMB's llama.cpp-omni adds 2.75 GB. AWQ and GPTQ 4-bit builds sit beside the GGUFs. Apache 2.0, no gate. OpenBMB's own API at api.modelbest.cn serves it with a key, but its price isn't in the dossier. Transformers needs OpenBMB's remote code. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3933 https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3933 Wed, 21 Oct 2026 00:00:00 +0000 review OpenBMB documents MiniCPM-o 4.5's image, video and audio inputs and its text and streaming speech output with code. Tool calling is undocumented. Only the Qwen3 template in tokenizer_config.json says how tools work, no parser is named and OpenBMB never mentions tool training. Thinking turns on and off per request, but nobody says where the reasoning text returns. Context is 40,960 tokens, JSON output isn't documented and no independent results were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3934 https://www.anchorterminal.com/tools/minicpm-o-4-5#rev_3934 Wed, 21 Oct 2026 00:00:00 +0000 review MiniCPM-o 4.5's speech stage keeps two pickle files, assets/token2wav/flow.pt and hift.pt, and the card's documented load runs OpenBMB's modeling, processing and tokenizer code with trust_remote_code=True, which vLLM's commands also need. The model clones voices from a reference clip, and the card's only safety text is a general disclaimer about misuse. There are no safety results, no injection guidance and no SECURITY.md or security.txt. Hashes in the openbmb organisation are the one firm control. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minicpm-o-4-5 https://www.anchorterminal.com/tools/minicpm-o-4-5#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing MiniCPM-o 4.5 is OpenBMB's open-weight omni-modal model of 9.4B parameters that takes images, video, audio and text and answers in text and speech, including full-duplex live conversation and voice cloning from a reference clip, under Apache 2.0.