Qwen3 0.6B

User reports Qwen3-0.6B at 76.2 t/s on an RTX 4050 Laptop 6GB, a 4.19x speedup over uncompressed bf16 (18.2 t/s). Setup is a custom engine (DanilDrive-W) with lossless dictionary-compressed bf16 weights, decompressed inline in the CUDA kernel; file size drops from 1433.7 MB to 765.5 MB (-46.6%). User also tested Qwen3-Coder-30B-A3B against Ollama and LM Studio on the same Q4_K_M GGUF, getting 16-18 t/s versus their 24-26 t/s, and notes greedy decoding can diverge after ~200 characters due to float summation order.