DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Zero data retention is available on eligible routes; output limits and reasoning levels depend on the selected route. Released under the MIT license.
DeepSeek V4.1 Flash 1017 Thinking
deepseek/deepseek-v4.1-flash-1017:thinkingThe October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Zero data retention is available on eligible routes; output limits and reasoning levels depend on the selected route. Released under the MIT license.
Elorian Glimpse
elorian/glimpseGlimpse is Elorian's visual reasoning model for understanding images and video and answering in text. It can analyze charts, count objects, follow events over time, and reason about spatial relationships and physical cause and effect. It supports tool calling and structured output across a shared 262,144-token context window, with up to 256,000 output tokens within the remaining context.
Qwen 3.8 27B Uncensored Fast by Heabsy
heabsy/qwen3.8-27b-uncensored-fastHeabsy's NVFP4 build of Qwen3.8-27B by Alibaba Cloud, with refusal removal based on huihui-ai's Huihui-Qwen3.8-27B-abliterated. Quantized and calibrated by Heabsy, with unpublished weights under the Heabsy Model License. Supports text and image input, tools, and optional reasoning capped at 16,384 tokens within the output budget. This named build is separate from Qwen 3.8 27B Uncensored.
Moondream 3 Preview
moondream/moondream3-previewMoondream 3 Preview is the original 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.
Moondream 3.1 9B A2B
moondream/moondream3.1-9b-a2bMoondream 3.1 is the successor to Moondream 3 Preview: a distinct 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.
