Post @onusoz · /2026/07/31 · 05:21 PM View on The 3-bit one leave just enough space for me to browse twitter on the dgx spark, perfect @UnslothAI · Jul 31, 2026 DeepSeek V4 Flash 0731 can now be run locally! š³ Run DeepSeek V4 Flash lossless 4-bit on 168GB RAM and 3-bit on 110GB RAM. V4 Flash 0731 outperforms V4 Pro. Run via Unsloth or llama.cpp. Smaller quants coming today. Guide: unsloth.ai/docs/models/de⦠GGUF: huggingface.co/unsloth/DeepSe⦠Show more Image hidden
@onusoz · /2026/07/31 · 05:21 PM View on The 3-bit one leave just enough space for me to browse twitter on the dgx spark, perfect @UnslothAI · Jul 31, 2026 DeepSeek V4 Flash 0731 can now be run locally! š³ Run DeepSeek V4 Flash lossless 4-bit on 168GB RAM and 3-bit on 110GB RAM. V4 Flash 0731 outperforms V4 Pro. Run via Unsloth or llama.cpp. Smaller quants coming today. Guide: unsloth.ai/docs/models/de⦠GGUF: huggingface.co/unsloth/DeepSe⦠Show more Image hidden