https://www.anchorterminal.com/tools/ling-3-0-tiny Dated changes, score moves with their causes, what our workers noticed, and reviews for Ling-3.0-tiny. en Wed, 21 Oct 2026 22:14:21 +0000 https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3923 https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3923 Wed, 21 Oct 2026 00:00:00 +0000 review inclusionAI last changed the repository on 24 September 2026, adding a training-content summary to the card. The card's SGLang recipe calls for built-in MTP, while config.json sets num_nextn_predict_layers to 0 and the index holds no MTP tensors. The index's total_size reads 3,869,925,683,584 bytes against 15,787,992,416 in the shards, reported in discussion 18. One of 16 discussions has an inclusionAI reply, five an Ant Group member's, none after 18 August. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3924 https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3924 Wed, 21 Oct 2026 00:00:00 +0000 review inclusionAI's Q4_K_M GGUF is 4.82 GB, about 5.8 GB with a fifth added, and its INT4 safetensors build is 5.82 GB, so an 8 GB machine covers either. FP8, Q5_K_M, Q6_K and Q8_0 come from inclusionAI too. MIT with nothing added, no gate. Transformers, vLLM, SGLang and llama.cpp run it, and Ollama support is an unmerged pull request. OpenRouter lists it with no live endpoint. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3925 https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3925 Wed, 21 Oct 2026 00:00:00 +0000 review Ling-3.0-tiny's card names the ling3 tool parser in its commands without describing the format, while SGLang's cookbook uses glm45 for the same model. The template defines tools as JSON in a tools tag and calls as arg_key and arg_value pairs. enable_thinking false turns thinking off, but the card doesn't say where the reasoning returns. JSON output isn't documented. Seven independent Artificial Analysis results include 0.0 on Terminal-Bench 4.0. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3926 https://www.anchorterminal.com/tools/ling-3-0-tiny#rev_3926 Wed, 21 Oct 2026 00:00:00 +0000 review inclusionAI publishes Ling-3.0-tiny-singprobe, a streaming guardrail that scores query intent, response safety and hallucination per token for this model, yet the main card doesn't point to it. The card's vLLM command passes --trust-remote-code to run configuration_bailing_moe_v3.py, since vLLM 0.32.0 has no config of its own for it. The SGLang route avoids that. Files are safetensors and GGUF with hashes. No safety results for the model and no security contact. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ling-3-0-tiny https://www.anchorterminal.com/tools/ling-3-0-tiny#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Ling-3.0-tiny is inclusionAI's open-weight hybrid reasoning mixture of experts with 7.9B parameters and 1.3B active, mixing Kimi Delta Attention and MLA layers 3 to 1, with switchable thinking and a 131,072-token context, in BF16, FP8, INT4 and GGUF under MIT.