AI is happening. The future is updating.Qwen3.8-27B-Uncensored-DSpark-RTX5090
Target-matched ModelOpt NVFP4 DSpark speculative drafter for fleetml/Qwen3.8-27B-Uncensored-NVFP4-RTX5090. The drafter was initialized from RadixArk/Qwen3.8-27B-DSpark, trained in BF16 on hidden states captured from the exact OrcaRouter-derived NVFP4 target, and converted to ModelOpt NVFP4 for RTX 5090 serving. The current NVFP4 pair reached **217.73 tokens per second median decode** across 18 successful requests on one RTX 5090.
Target-matched ModelOpt NVFP4 DSpark speculative drafter for fleetml/Qwen3.8-27B-Uncensored-NVFP4-RTX5090. The drafter was initialized from RadixArk/Qwen3.8-27B-DSpark, trained in BF16 on hidden states captured from the exact OrcaRouter-derived NVFP4 target, and converted to ModelOpt NVFP4 for RTX 5090 serving. The current NVFP4 pair reached **217.73 tokens per second median decode** across 18 successful requests on one RTX 5090.