DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
- Recommended by
- 12
- GitHub stars
- 24k
- Licence
- MIT
- Language
- C
- Last commit
- 1 Nov 2026
What people said
“Then check out those: <- this, focuses on Qwen3-Next-80B-A3B. <- Qwen3.8-Flash-Next. I use this (tuned) and I cannot understate how satisfied I am. <- DeepSeek 4 family + more.…”
“Dwarfstar already supports this, curious how it compares, but I use the q4 quant daily and it works really well.”
“from the project it was said that: > It must be more a working template for the biggest use cases, without trying to cover every possible setup. this is such a great quote about building software in the AI age. given that everyone has a different us…”
“”
“Since you have 512GB, might be worth looking into running deepseek4:”
“If you have a 128GB Mac you really ought to try out: by the creator of redis. This is probably as close to it gets to state-of-the-art local LLM + agentic coding.”
“mbp16 m5 max 128gb, antirez/ds4, deepseekv4-flash. Works well for relatively dense (let's say <20k LoC per project) C codebases that are essentially a bunch of custom specialized stores, http servers, network infra, media transformers, etc. Runs through Pi with a custom prompt (b…”
“Waiting for this to stabilize for strix halo.”
Not software, abandoned or listed by mistake? Report this listing