https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b Dated changes, score moves with their causes, what our workers noticed, and reviews for Ornith-1.5-35B-A3B. en Wed, 21 Oct 2026 21:48:42 +0000 https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3971 https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3971 Wed, 21 Oct 2026 00:00:00 +0000 review Ornith released on 19 August 2026 and between 23 and 26 August replaced a main shard, every GGUF file, an FP8 shard and the NVFP4 shards in place, with no note on any card. The last change to the model's files was that NVFP4 re-upload on 26 August, 56 days ago. None of the 35 discussions has an Ornith reply. The card links a LICENSE that returns 404, and the two chat templates disagree on keeping earlier reasoning. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3972 https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3972 Wed, 21 Oct 2026 00:00:00 +0000 review Ornith publishes the full range itself, from FP8 at 39.4 GB down to an MLX 4-bit build at 19.5 GB, which fits 24 GB but runs only on Apple silicon. Its Q4_K_M GGUF is 21.7 GB and Ollama's build 23 GB, both in the 32 GB band. The card's metadata says MIT, but the repository has no LICENSE file, the licence link returns 404 and the Qwen3.5 base's Apache 2.0 notice isn't carried. No provider hosts it. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3973 https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3973 Wed, 21 Oct 2026 00:00:00 +0000 review Ornith's card shows tools declared in the OpenAI tools array, calls returned in tool_calls, and names qwen3_xml for vLLM and qwen3_coder for SGLang. Its template renders several calls in one turn and turns thinking off with enable_thinking false, a switch the card doesn't name. chat_template.jinja keeps earlier reasoning while the tokenizer_config.json copy drops it. JSON output isn't documented. Nobody independent has benchmarked it, and the card's MCP-Atlas and Terminal-Bench figures are Ornith's claims. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3974 https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#rev_3974 Wed, 21 Oct 2026 00:00:00 +0000 review Ornith-1.5-35B-A3B ships safetensors, GGUF and MLX files with no Python, and the card's --trust-remote-code flag has no code to load. Every weight file has a SHA-256. The ornith-ai organisation isn't verified, no legal entity is named, and the MIT licence link returns 404, with no notice for the Qwen3.5 base. The card points the model at Claude Code, OpenCode and other agent harnesses but gives no cautions, no safety results 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/ornith-1-5-35b-a3b https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Ornith-1.5-35B-A3B is Ornith's open-weight mixture-of-experts reasoning model for coding and agent work, about 35B parameters with 3B active per token on Qwen3.5's architecture, with a 262,144-token context, published in BF16, FP8, NVFP4, GGUF and MLX and marked MIT.