@Prince_Canuma: My home compute for MLX and research: • M3 Ultra — 512GB (sponsored by community + @wai_protocol) • RTX PRO 6000 — 96GB…
Summary
A researcher shares their home compute setup for MLX and AI research, featuring M3 Ultra with 512GB, RTX PRO 6000 with 96GB, and M3 Max with 96GB for model porting and stress testing.
Similar Articles
2x 512gb ram M3 Ultra mac studios
A user shares their $25k hardware setup of two 512GB RAM M3 Ultra Mac Studios for running large language models locally, having tested DeepSeek V3 Q8 and GLM 5.1 Q4 via the exo distributed inference backend, while awaiting Kimi 2.6 MLX optimization.
@ashxhart: Been giving my M3 Ultra Studio some love and tinkering with MLX. Started the afternoon at 42 tok/s. Now: 73 tok/s, and …
An author improved MLX performance on an M3 Ultra Studio to achieve 73 tok/s for a 4-bit Qwen3.8-Flash-Next model, which shows intelligence scores matching GPT-5.6 Sol, highlighting the growing potential of local AI.
@volatilemarkts: Same Mac. Same model. Same words. My 512 GB M3 Ultra ran GLM-5.3-Flash on MLX last week: 27 tok/s, first token in 0.46 …
TensorFold 0.6.2 is an Apache 2.0 open-source LLM inference engine claiming over 2x faster token throughput than MLX on Apple Silicon (61 vs 27 tok/s on an M3 Ultra) via multi-token-prediction speculative decoding, with parallel concurrent requests and OpenAI-compatible API.
4x 6000 Pro for the company
A user shares how they serve 40 employees (10 developers) with a fully local AI stack powered by a 4U server with 4x RTX 6000 Blackwell MaxQ GPUs (384GB VRAM), running DeepSeek V4 Flash via vLLM, Qwen 3.8 27B and K2-Horizon 7B via llama.cpp, plus n8n automation, OpenWebUI, Whisper/Vexa AI Teams transcription, and ComfyUI for marketing.
I have just moved from MacBook M5 pro 48 GB to RTX3090
A software developer shares their experience switching from a MacBook to an RTX3090 Linux setup for running AI models, achieving significantly higher inference speeds with Qwen 3.8 27B and potentially replacing their Claude subscription.