WikiBench 1.0: locally quantized DeepSeek V4.1 Flash beats its cloud version
On a 100-task, 12-model board, DeepSeek V4.1 Flash running locally at EXL3 1.62bpw without thinking on one ASUS Ascent GX10 scored 5.37, topping the list and beating its cloud version's 5.01 by 0.36.
WikiBench 1.0 is live. 100 real tasks, 12 weighted categories, 12 models on the board. The top five: 1. DeepSeek V4.1 Flash (EXL3 1.62bpw, no thinking), local on one ASUS Ascent GX10: 5.37 @ViC305 2. NVIDIA Nemotron 3.5 Lightning 30B-A3B (NVFP4), local on the same GX10: 5.03 3. DeepSeek V4.1 Flash, cloud via Nous Portal: 5.01 4. Meituan LongCat 2.5 Preview, cloud via Nous Portal: 4.99 5. Ornith 1.5 122B (Q4), local on the GX10: 4.88 The same DeepSeek V4.1 Flash, cut down to 1.62 bits so it fits in 128GB, beat its own cloud version by 0.36. And a 30B model on my desk still sits ahead of every cloud model on the board. Three of the top five never left the box. Full scoreboard, local vs cloud, method and the link below. Credit to all your crazy people working with a DGX Spark!