@antirez: DS4 is now called DwarfStar4, since you can put a lot of mass into a tiny space... And in a few minutes it is going to …
Summary
Antirez announces the renaming of DS4 to DwarfStar4 and teases improved 2-bit quantization for 128GB Macs using an in-house iMatrix method.
Similar Articles
A few words on DS4
Antirez announces DwarfStar 4 (DS4), a local AI tool that runs DeepSeek v4 Flash with asymmetric 2/8 bit quantization on high-end consumer hardware, achieving near-frontier performance. He discusses the project's rapid popularity, future plans for model updates and distributed inference, and the significance of local AI for serious tasks.
@ttasanen: Just fired up DS4 by @antirez on my Mac Studio M3 Ultra 256GB and man, it’s seriously impressive. A clean, purpose-buil…
DS4 is a specialized inference engine by antirez designed to run DeepSeek V4 Flash locally on high-end Mac hardware, featuring optimized KV cache handling and 1M context support.
@antirez: Based on what I'm saying with GLM 5.2 implementation inside DwarfStar, there is 90% of probability I'll merge the branc…
Antirez announces high probability of merging a branch implementing GLM 5.2 in DwarfStar, which could become the best model for 512GB Mac Studio and potentially run on distributed 128GB MacBooks with 2-bit quantization.
DS4
Salvatore Sanfilippo released DS4, a project enabling DeepSeek V3 (referred to as V4 in text) Flash to run with a 1M context window on Mac Metal hardware, with potential for DGX and AMD support.
@antirez: DS4 running on DGX Spark (GB10 / CUDA), private branch for now. 12 tokens/sec, the memory bandwidth is limited in this …
Antirez reports benchmarking DS4 inference on the DGX Spark (GB10), noting 12 tokens/sec generation speed and high prefill performance, with plans to merge the codebase once mature.