Model Releases
@badlogicgames Yup: https://x.com/antirez/status/2048344770234249588 The GGUF tool calling template is wrong but I'm uploading a new GGUF fi…
@badlogicgames Yup: https://x.com/antirez/status/2048344770234249588 The GGUF tool calling template is wrong but I'm uploading a new GGUF file. Otherwise there is the right template file in one of the
@badlogicgames Yup: https://x.com/antirez/status/2048344770234249588 The GGUF tool calling template is wrong but I'm uploading a new GGUF file. Otherwise there is the right template file in one of the latest commits and there is to specify it when executing llama.cpp. Uploading the fixed file ASAP btw on HF. Here you can find experimental support for DeepSeek v4 Flash in llama.cpp: https://github.com/antirez/llama.cpp-deepseek-v4-flash And a GGUF file you can use in order to run the inference with just 128 GB of RAM: https://huggingface.co/antirez/deepseek-v4-gguf Check the first par…
Source: Clem Delangue (X) | 2026-04-26