ModelDeepSit V4.1 Flash
DeepSit V4.1 Flash
An inference-optimized model released by Unslough. Paired with Dynamic V3.1 quantization technology, it performs leadingly on mainstream benchmarks, supports local inference with ordinary 64 GB memory, and offers a threefold speed increase.
Timeline (last 90 days)
Oct 31
OpenCode announced that users can directly use their own Claude subscription accounts without repeatedly purchasing third-party APIs, and launched phase four of its campaign, with the included DeepSit V4.1 Flash allowance surging to $100; version 2.2.3 also includes a built-in image generation tool, connecting to image models such as OpenAI, Gemini and Grok.
Unverified50%