Dev
Tooling, languages, APIs and the daily craft of building software.
Granite Switch 4.1 won’t install next to this month’s vLLM
IBM released Granite Switch 4.1 on 15 October. The model cards pin vLLM below 0.28, the plugin allows up to 0.30, and neither covers vLLM 0.31.0. Speech is English only.
Read moreDetailsBeam’s weights are out, and vLLM support is still an open pull request
Reflection published Beam 1.0 weights on 16 October: 1,002.68 GB in BF16, 293.65 GB in NVFP4, plain Apache 2.0. Transformers 5.20.1 loads it; the vLLM day-0 support is an unmerged...
Read moreDetailsIs Opus 5.5 fast mode worth $40 per million output tokens?
Since 15 October, fast mode on Claude Opus 5.5 needs no waitlist or beta header. We stacked every multiplier on the $8/$40 price and found the catch: fast and standard...
Read moreDetailsFine-tune on Muse Spark Open outputs and you owe Meta a credit line
Muse Spark Open went up on Hugging Face on 15 October under an MIT-style licence with three strings: a Built with credit that follows models trained on its outputs, a...
Read moreDetailsNemotron 3.5 Bolt says 24GB on the label and 28GB in the recipe
NVIDIA released Nemotron 3.5 Bolt 74B-A9B on 15 October. The files the recipe loads total 24.75 GB, there is no 24 GB discrete recipe, and the PinchBench #1 claim trails...
Read moreDetailsMeta’s API sells Muse Wonder, not the Wonder Full that tops its chart
Meta launched Muse Wonder and Muse Wonder Full on 12 October. We read the model card and the price page: the API gets the weaker one, and the benchmark footnotes...
Read moreDetailsLFM2.5-24B-A2B beats Qwen3.6 at tools and loses SWE-Bench by 15 points
Liquid AI released LFM2.5-24B-A2B with open weights. We read the full benchmark table and the license: strong at tool calls, weak at coding, and not free for every company.
Read moreDetailsRequests to gemini-3.7-flash now get 3.8 Flash, with no shutdown date
Google deprecated Gemini 3.7 Flash on 8 October and routes its traffic to 3.8 Flash, a month after calling 3.7 the efficiency pick. Here's what moves on the bill and...
Read moreDetailsOpenAI’s Decisions API charges $0.10 in and nothing out, with no cache
Decisions returns a probability, a choice or a score instead of text, on gpt-6-luna only. It's $0.10 in and free out, but with no caching a long rubric can cost...
Read moreDetailsGPT-6.1 Sol Ultrafast bills six times Sol and 1.2 times Astra
Ultrafast on GPT-6.1 Sol costs $12 and $60 per million tokens: six times standard Sol, three times Fast, and 1.2 times Astra at normal speed. The guide is silent on...
Read moreDetails