@alexocheema: Running Qwen3.6 35B (vision) on 2 x M5 Max MacBook Pro with RDMA over Thunderbolt 5. It describes the image and identif…
Summary
A demo shows Qwen3.6 35B vision model running across two M5 Max MacBook Pros connected via RDMA over Thunderbolt 5, achieving near-instant responses with prefix caching. The model correctly identifies Apple Park but misidentifies a person in the image.
Similar Articles
@remilouf: Following @julien_c’s tweet I bought a MacBook Pro with 128B unified memory, and started running Qwen3.6 as my daily dr…
The author shares their experience running the Qwen3.6 model on a MacBook Pro with 128GB of unified memory, praising Apple's hardware efficiency for local AI inference.
Ran Qwen3.8-Flash-Next (79 GB, 2-bit) at 350K ctx for 3.5 hours on a 128 GB M5 Max — speed vs context depth, 100 turns, one graph
This article reports on running the Qwen3.8-Flash-Next model on a MacBook Pro M5 Max, benchmarking speed versus context depth over 100 turns, with insights into performance and issues like role confusion at long contexts.
@AlexJonesax: Qwen3.6-27b absolutely flying on a M5Max with MTP enabled & oMLX inference.
A community report highlights high inference performance for the Qwen3.6-27b model on M5Max hardware using oMLX optimization.
Running Qwen 3.6 35B MoE (Q4_K_M) on a Zeus (Xiaomi 12 Pro, 12GB RAM)
Demonstrates running the Qwen 3.6 35B MoE model in Q4_K_M quantization on a Xiaomi 12 Pro with 12GB RAM, showing local AI inference on a mobile device.
Running Qwen 3.6 35b MoE With Zoo Code On M1 Max is Amazing! Fully local, battery-powered coding powerhouse!
The article discusses running the Qwen 3.6 35b Mixture-of-Experts model locally on an Apple M1 Max Mac using Zoo Code, highlighting its capabilities as a battery-powered coding assistant.