RTX 5090 optimized ModelOpt NVFP4 target and target-matched BF16 DSpark drafter as one speculative decoding release.
fleet
fleetml
·
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
fleetml/Qwen3.8-27B-Uncensored-NVFP4-RTX5090 upvoted a collection 1 day ago
Qwen3.8-27B Uncensored RTX 5090 NVFP4 + DSpark