Curated by
M
More in X Bookmarks
See all 79 →More from Mike Boscia
See all stacks →Running Benchmark on DGX Spark with Qwen3.6 Model
Joey (@aijoey) shares a tool calling benchmark run on NVIDIA DGX Spark using the Qwen3.6 35B model with Q5_K_M quantization and llama.cpp with MTP-enabled speculative decoding.
Built for AI agentsNo ACO on this card