https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next Dated changes, score moves with their causes, what our workers noticed, and reviews for Swift 1.5 Qwen3.8-Flash-Next. en Thu, 22 Oct 2026 00:02:21 +0000 https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4083 https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4083 Wed, 21 Oct 2026 00:00:00 +0000 review UkisAI released this in one commit on 24 September 2026 and later renamed the repository from Swift-Qwen3.8-Flash-Next to Swift1.5-Qwen3.8-Flash-Next with no note. The old name redirects and the card's commands still use it. The re-serialised tokenizer.json drops combining marks from the pre-tokenizer pattern while the repository's own tokenizer config and the base keep them. None of the 3 discussions has a reply. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4084 https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4084 Wed, 21 Oct 2026 00:00:00 +0000 review Two licences stack here. UkisAI's covers free commercial use below US$1,000,000 gross annual revenue, and the base's Qwen Community License 1.0 needs a separate licence from Qwen for Model as a Service or AI Work Assistant businesses. Neither licence price is published. The smallest 4-bit build is a 98.6 GB IQ4_XS GGUF, about 118.3 GB with the margin, and BF16 is 360 GB. UkisAI's API is for research only and wasn't called. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4085 https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4085 Wed, 21 Oct 2026 00:00:00 +0000 review Two parsers appear on the card, qwen3_xml in the vLLM command and qwen3_coder in the SGLang one, and neither format is described outside the base template. reasoning_effort budgets thinking per request through chat_template_kwargs, but turning it off and where the reasoning returns aren't documented. tokenizer.json uses a pre-tokenizer pattern without combining marks, unlike its own tokenizer_config.json and the base, so the text the model reads may differ by loader. Nobody independent has benchmarked 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/swift-1-5-qwen3-8-flash-next#rev_4086 https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#rev_4086 Wed, 21 Oct 2026 00:00:00 +0000 review Swift 1.5 Qwen3.8-Flash-Next's 131 safetensors shards hold no Python, and the card's --trust-remote-code has no auto_map to act on. UkisAI's site links the account, and every LFS file is hashed. The licence chain carries UkisAI's US$1,000,000 revenue limit plus the Qwen Community License, which needs a separate licence for a Model as a Service or AI Work Assistant business. There are no safety results, no injection guidance, and only a general contact address. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Swift 1.5 Qwen3.8-Flash-Next is UkisAI's post-trained Qwen3.8-Flash-Next that aims to think in fewer tokens, a mixture-of-experts vision-language model of 180B parameters in its files with a 262,144-token context, published in BF16 with GGUF, INT4 and NVFP4 builds.