Red Hat AI(@RedHat_AI):Pair the DSpark speculator with our GLM-5.3 NVFP4 checkpoint for the best vLLM performance on Blackwell. NVFP4 gives you a 4-bit target that recovers 95%+ of accuracy across evals. DSpark adds faster decoding on top. To run both: serve RedHatAI/GLM-5.3-NVFP4 and set --speculative-config to method dspark with the GLM-5.3-speculator.dspark model (8 tokens). Full config on the card:

2026.09.24 13:51

Pair the DSpark speculator with our GLM-5.3 NVFP4 checkpoint for the best vLLM performance on Blackwell. NVFP4 gives you a 4-bit target that recovers 95%+ of accuracy across evals. DSpark adds faster decoding on top. To run both: serve RedHatAI/GLM-5.3-NVFP4 and set --speculative-config to method dspark with the GLM-5.3-speculator.dspark model (8 tokens). Full config on the card:

Red Hat AI@RedHat_AI

2026.09.17 17:23

🚀 D-Spark for GLM-5.3 beats native MTP on 8×B300: 29% faster single-stream decoding and 16% higher peak throughput. On MRCR, acceptance holds through 1M context, averaging 4.293 accepted tokens in the 524K–1M bucket. Try this out and let us know! 🤗