{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T14:06:34.317Z","data":{"recordId":"wsa_7i4g4y3kw77z","score":0.958,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/zai-org/GLM-5.3-Flash","publisher":"Z.ai","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-27T01:28:35.740Z","detectedPublishedAt":"2026-08-25T06:43:14.000Z","rights":"original"},{"n":2,"url":"https://huggingface.co/zai-org/GLM-5.3-Flash-BF16","publisher":"Z.ai","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-09-24T13:37:25.441Z","detectedPublishedAt":"2026-08-25T06:45:05.000Z","rights":"original"},{"n":3,"url":"https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4","publisher":"NVIDIA","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-27T01:28:35.740Z","detectedPublishedAt":"2026-09-02T20:37:17.000Z","rights":"original"},{"n":4,"url":"https://github.com/mw00/project-maya","publisher":"GitHub new repositories","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-27T01:28:35.740Z","detectedPublishedAt":"2026-10-06T22:55:13.000Z","rights":"original"},{"n":5,"url":"https://huggingface.co/nvidia/GLM-5.3-Flash-FP4-Local","publisher":"NVIDIA","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-27T01:28:35.740Z","detectedPublishedAt":"2026-10-08T16:19:57.000Z","rights":"original"},{"n":6,"url":"https://docs.mistral.ai/resources/changelogs#2026-10-22","publisher":"Mistral","authority":"other","verification":"verified","lastRetrievedAt":"2026-10-27T01:28:35.740Z","detectedPublishedAt":"2026-10-22T00:00:00.000Z","rights":"original"}],"claims":[{"id":"13e4fd65-7d2b-47c2-927d-c456c6de6fcf","kind":"availability","statement":"The checkpoint was released on Hugging Face on 10/05/2026.","citations":[{"source":5,"supportProbability":0.95,"supports":true,"quote":{"text":"Dataset disclosures are published in the `nvidia/nemotron-post-training-v2` and subset of `nvidia/nemotron-post-training-v3` and subset of `nvidia/nemotron-pre-training-datasets` Hugging Face collections.","rights":"original"}}]},{"id":"d0d46481-9074-4b5d-b367-326514807616","kind":"deployment","statement":"The checkpoint is best suited for local AI hardware and uses approximately 166 GiB of vRAM.","citations":[{"source":5,"supportProbability":0.96,"supports":true,"quote":{"text":"This checkpoint is best suited for local AI hardware and uses approximately **166 GiB of vRAM**.","rights":"original"}}]},{"id":"5bebf606-e553-4868-a01e-53761fa8f2e7","kind":"deployment","statement":"The checkpoint requires provided community vLLM containers because upstream support for its NVFP4 scale-factor format has not yet landed.","citations":[{"source":5,"supportProbability":0.97,"supports":true,"quote":{"text":"**IMPORTANT**: the NVFP4 scale factors in this checkpoint are in a new lossless compression format, but upstream vLLM support for this format has not yet landed.","rights":"original"}}]},{"id":"9853e750-97f2-462c-8484-65500f181395","kind":"recommendation-relevant","statement":"The checkpoint is ready for commercial or non-commercial use under the stated NVIDIA Open Model Agreement download terms.","citations":[{"source":5,"supportProbability":0.75,"supports":true,"quote":{"text":"**GOVERNING DOWNLOAD TERMS:** Use of this model is governed by [NVIDIA Open Model Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/).","rights":"original"}}]},{"id":"3a0cb952-f3d0-4b76-88c3-9eefef310035","kind":"capability","statement":"The model is a quantized version of ZAI's GLM-5.3-Flash.","citations":[{"source":3,"supportProbability":0.99,"supports":true,"quote":{"text":"The NVIDIA GLM-5.3-Flash NVFP4 model is the quantized version of ZAI's GLM-5.3-Flash model, which is an auto-regressive language model that uses an optimized transformer architecture.","rights":"original"}},{"source":5,"supportProbability":0.93,"supports":true,"quote":null}]},{"id":"17cfb7ff-b495-45bc-bacf-336a8ad2e265","kind":"capability","statement":"It accepts text, image, and video inputs and supports context lengths up to 1M.","citations":[{"source":3,"supportProbability":0.97,"supports":true,"quote":null},{"source":5,"supportProbability":0.75,"supports":true,"quote":null}]},{"id":"a3ebcb1e-6d34-4821-84ea-d8573705d772","kind":"deployment","statement":"The checkpoint supports vLLM and SGLang.","citations":[{"source":3,"supportProbability":0.93,"supports":true,"quote":{"text":"To serve this checkpoint with [vLLM](https://github.com/vllm-project/vllm), start from `vllm/vllm-openai:glm53-flash-arm64-cu130`   and run:","rights":"original"}}]},{"id":"7472b4c2-c2ca-443a-9267-f8275bc19786","kind":"recommendation-relevant","statement":"The model is optimized for NVIDIA Blackwell hardware.","citations":[{"source":3,"supportProbability":0.5,"supports":false,"quote":{"text":"The NVIDIA GLM-5.3-Flash NVFP4 model is the quantized version of ZAI's GLM-5.3-Flash model, which is an auto-regressive language model that uses an optimized transformer architecture.","rights":"original"}}]},{"id":"f1223342-aa0b-4a0b-8814-36009fce91a7","kind":"recommendation-relevant","statement":"NVFP4 quantization reduces disk size and GPU memory requirements by approximately 3.33x.","citations":[{"source":3,"supportProbability":0.99,"supports":true,"quote":{"text":"This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 3.33x.","rights":"original"}}]},{"id":"ec0c19d1-d4ec-47b2-9731-7a78bc11ae17","kind":"availability","statement":"The listed Hugging Face release date is 09/09/2026.","citations":[{"source":3,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"ef8d2651-9bcb-4faa-8c58-665cf6293561","kind":"pricing","statement":"Z.ai says GLM-5.3-Flash is available at one-tenth the price of GLM-5.2.","citations":[{"source":1,"supportProbability":0.87,"supports":true,"quote":null}]},{"id":"0f9188e6-b17b-4808-a170-9d03043f673f","kind":"capability","statement":"GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"We introduce GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series.","rights":"original"}}]},{"id":"90209863-84e6-401b-ab07-157fa31e8903","kind":"capability","statement":"The model has 320B total parameters and 18B active parameters.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks.","rights":"original"}},{"source":5,"supportProbability":0.86,"supports":true,"quote":null},{"source":6,"supportProbability":0.88,"supports":true,"quote":null}]},{"id":"79cacb62-047a-4d99-af2c-79a2575b7f71","kind":"capability","statement":"It supports controlling the thinking budget with the reasoning_effort parameter at low, high, and max levels.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- GLM-5.3-Flash supports controlling the thinking budget through the `reasoning_effort` parameter, which accepts three levels: `low`, `high`, and `max`.","rights":"original"}}]},{"id":"33f0ea0f-0c8c-4532-8dfb-1c75546c34a5","kind":"availability","statement":"GLM-5.3-Flash API services are available on the Z.ai API Platform.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"📍 Use GLM-5.3-Flash API services on <a href=\"https://docs.z.ai/guides/llm/glm-5.3-flash\">Z.ai API Platform.","rights":"original"}}]},{"id":"793acc68-910d-4815-b8de-cb1af4237e3d","kind":"deployment","statement":"The model supports local deployment with SGLang, vLLM, TokenSpeed, Transformers, KTransformers, and Unsloth.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":null}]},{"id":"a1e2b0b8-61dd-493a-965e-52e43ea0abc1","kind":"capability","statement":"Project Maya provides an OpenAI- and Anthropic-compatible API with tool calls.","citations":[{"source":4,"supportProbability":0.99,"supports":true,"quote":{"text":"- **Plugs into your tools:** OpenAI- and Anthropic-compatible API with tool calls, ready for coding agents.","rights":"original"}}]},{"id":"3b09c692-8054-4a64-9236-dd948ebfbc65","kind":"capability","statement":"The application includes browser chat and a live monitor.","citations":[{"source":4,"supportProbability":0.96,"supports":true,"quote":{"text":"- **Everything in the box:** a chat and a live monitor in the browser, pictures, thinking levels, a one-command setup.","rights":"original"}}]},{"id":"8273cfd6-2def-4695-b64b-663125db770e","kind":"deployment","statement":"Project Maya runs models using GPU, RAM, and NVMe storage on the user's machine.","citations":[{"source":4,"supportProbability":0.95,"supports":true,"quote":null}]},{"id":"5d4151bd-975c-4b5e-9d9e-60b346216aa0","kind":"privacy","statement":"The source says nothing leaves the user's machine.","citations":[{"source":4,"supportProbability":0.97,"supports":true,"quote":{"text":"Nothing leaves your machine.","rights":"original"}}]},{"id":"81460f53-4323-464d-b7ce-4b29451a63b3","kind":"pricing","statement":"Project Maya is free.","citations":[{"source":4,"supportProbability":0.99,"supports":true,"quote":{"text":"<sub>Project Maya is free.","rights":"original"}}]},{"id":"5806709d-a251-487a-bd32-84339ded88d2","kind":"capability","statement":"The setup offers GLM-5.3-Flash, DeepSeek-V4.1-Flash-1017, and experimental MiniMax-M3.1-Flash support.","citations":[{"source":4,"supportProbability":0.86,"supports":true,"quote":{"text":"The setup also offers **[DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017)**","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}