For a single Spark my first recommendation would be Qwen 3.5 122B MoE (Int4) For the Mac Studio I would recommend the 397B in 4-bit (and I think @ivanfioravanti would agree with me here)
@theahmadosman
-
Use MoE Models on Unified Memory Hardware Like DGX Spark
By
–
As I have mentioned before, stop trying to get Dense models running on the DGX Spark/Mac Studios Unified Memory is best fit for MoEs because you only make each token go through a small subset of the numbers of parameters in the model Optimize for your hardware
-
27B Parameters Per Token Explains Slow LLM Inference Speed
By
–
Ultimately you’re still going through the 27B parameters per token and that’s what takes so long
-
Qwen 3.5 27B Matches Sonnet 4.5 on Single RTX 5090
By
–
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
-
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
-
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
-
Open Source Inference Still Immature: Hardware and Optimization Needed
By
–
Not saying not to use it, but expect inaccuracies Doing this right requires actual hardware + knowing which piece of the inference stack to optimize for the different hardware & goal We are still in the infancy stage of opensource inference, one day it will just work OOTB