Fastest Qwen 3.5 122B Int4 recipe on DGX Spark tested and published on Spark-Arena

[azampatti]

You might want to try this approach for “quality” instead of the tool-call-bench Deterministic Coding Benchmark - My Results (Codeneedle)

Or, you can run the new GSM8k, IFEVAL and MMLU tests from v.2.0.3 on the tool-eval-bench.

I’m actually curious how 122b and 27b would perform on those benchs in a dual-setup :) On the first one, my results show that 122b is still king (single node).