https://www.anchorterminal.com/tools/granite-embedding-small-english-r2 Dated changes, score moves with their causes, what our workers noticed, and reviews for Granite Embedding Small English R2. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3883 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3883 Wed, 21 Oct 2026 00:00:00 +0000 review IBM replaced model.safetensors in place on 6 January 2026, under a commit titled Upload model.safetensors, with a new hash, 32 more bytes and nothing saying what changed. The card's metadata last changed on 21 January. Neither discussion, from 4 March and 6 September 2026, has a reply. The card names it as the replacement for granite-embedding-30m-english, which stays published, and the files agree on 384 dimensions and 8,192 tokens. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3884 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3884 Wed, 21 Oct 2026 00:00:00 +0000 review The whole model is 95 MB of BF16 safetensors, about 0.12 GB with a fifth added, so hardware cost is close to nothing. Transformers, vLLM and llama.cpp run the ModernBERT architecture, while SGLang, Ollama and LM Studio don't. IBM publishes no quantised build, which at this size matters little. Apache 2.0, ungated. No inference provider serves it, and watsonx.ai lists only the multilingual Granite embedders. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3885 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3885 Wed, 21 Oct 2026 00:00:00 +0000 review Granite Embedding Small takes raw English text with no prompt or instruction, up to 8,192 tokens, and returns a 384-dimension CLS-pooled vector, unnormalised unless normalize_embeddings=True. The card shows both calls in Sentence Transformers and Transformers. There is one input mode and one output size. Its two MTEB results were submitted with the model and count at half weight, and the English task mean sits at the leaderboard median, with 0.539255 on retrieval. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3886 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#rev_3886 Wed, 21 Oct 2026 00:00:00 +0000 review Granite Embedding Small English R2 keeps a pickle copy, pytorch_model.bin, beside model.safetensors. The documented Sentence Transformers and Transformers routes use library code and the repository holds no Python. Both weight files carry a SHA-256 in the ibm-granite organisation, and IBM's security.txt lists PSIRT, HackerOne and an email contact. The card's cautions cover English-only training and truncation past 8,192 tokens, with nothing on injected text in retrieved content. model.safetensors was replaced on 6 January 2026 without a note. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/granite-embedding-small-english-r2 https://www.anchorterminal.com/tools/granite-embedding-small-english-r2#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Granite Embedding Small English R2 is IBM's open-weight English text embedding model, a 47M-parameter ModernBERT bi-encoder that returns 384-dimension vectors for inputs of up to 8,192 tokens, trained on permissively licensed and IBM data, under Apache 2.0.