That model, Qwen 3.5 27B Dense is equal to Sonnet 4.5 Runs great on a single RTX 5090 w/ full context But we are not anywhere near Opus 4.5 even with Qwen 3.5 397B MoE
HARDWARE
-
DGX Spark Qwen3 27B Inference Speed Discrepancy Questioned
By
–
Also, I don’t know how OP is getting Qwen3.5 27B @ 30 tps on the DGX Spark Doesn’t make sense for a Dense model on DGX Spark’s Unified Memory (273 Gbps) (My personal experiments showed it’s 4 tokens/sec) Very curious how you got that @TeksEdge
-
Qwen3 27B Performance Claims Disputed on DGX Spark Hardware
By
–
Also, I don’t know how OP is getting Qwen3.5 27B @ 30 tps on DGX Spark That number is impossible for a Dense model on DGX Spark’s Unified Memory (273 Gbps) My personal experiments showed it’s 4 tokens/sec for that model on the Spark
-
Unified Memory Faster for Loading Large MoE Models
By
–
the issue is that unified memory would still be faster for loading MoEs that are larger than the largest single GPU in terms of Memory
-
RTX PRO 6000 GPU Inference Faster Than Unified Memory After Loading
By
–
This will probably be great for Large single GPUs (e.g. RTX PRO 6000) You’re limited to 40Gpbs initially (during model loading) but then once the model is fully loaded on the GPU it should be extremely faster than Unified Memory speeds for inference
-
Stretchable Metal-Polymer Conductors: Breakthrough in Flexible Circuits
By
–
𝗜𝗺𝗽𝗿𝗲𝘀𝘀𝗶𝘃𝗲. 𝗪𝗶𝗿𝗲𝘀 𝘁𝗵𝗮𝘁 𝗱𝗼𝗻’𝘁 𝗯𝗿𝗲𝗮𝗸. 👏
— Pascal Bornet (@pascal_bornet) 14 mars 2026
Researchers in China have developed a Metal-Polymer Conductor (MPC) by combining elastic polymers with liquid metals like gallium and indium.
The result is quite remarkable.
A circuit that can:
→ stretch
→… pic.twitter.com/vxbbwC8eDX𝗜𝗺𝗽𝗿𝗲𝘀𝘀𝗶𝘃𝗲. 𝗪𝗶𝗿𝗲𝘀 𝘁𝗵𝗮𝘁 𝗱𝗼𝗻’𝘁 𝗯𝗿𝗲𝗮𝗸. Researchers in China have developed a Metal-Polymer Conductor (MPC) by combining elastic polymers with liquid metals like gallium and indium. The result is quite remarkable. A circuit that can: → stretch
→ -
Mac Mini with eGPU Support for NVIDIA and AMD
By
–
Mac Mini + eGPU. Both NVIDIA and AMD supported.
→ View original post on X — @jeremyphoward, 2026-03-14 04:16 UTC
-
H100 GPUs Have Appreciated in Value Over Three Years
By
–
> H100s are worth more today than they were 3 years ago https://t.co/UC8CiEw67R
— Ahmad (@TheAhmadOsman) 14 mars 2026> H100s are worth more today than they were 3 years ago
-
Impressions initiales positives, mais performance ralentie avec llama.cpp
By
–
I have a good first impression, but it's still a tad slow for me (using llama.cpp). About 2x slower than gpt-oss 120B on the same hardware. I think I need to look for the NVIDIA-optimized stack.
-
NVIDIA Partners with Universities to Accelerate AI Research
By
–
NVIDIA is partnering with universities worldwide to accelerate breakthroughs in AI, robotics, quantum, and more—fueling research with GPUs, grants, fellowships, and hands-on internships that turn ideas into real-world impact. “Universities are nothing less than spectacular when