🏗️ Building on HF

SolsticeAI

SolsticeAI

·

AI & ML interests

Real Intelligence, Built for the real world.

Recent Activity

updated a model 8 minutes ago

Solstice-AI/GLM-5.3-Flash-UNCENSORED-AWQ

updated a model 8 minutes ago

Solstice-AI/GLM-5.3-Flash-UNCENSORED-mlx-oQ8e-DFlash2

updated a model 9 minutes ago

Solstice-AI/GLM-5.3-Flash-UNCENSORED-NVFP4-DFlash2

View all activity

Organizations

New activity in Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M 41 minutes ago

More quants

#1 opened about 2 hours ago by

New activity in Solstice-AI/GLM-5.3-Flash-UNCENSORED-mlx-oQ4e-DFlash2 about 2 hours ago

Why does the file name include "Dspark" when I don't see any content related to Dspark?

#1 opened about 3 hours ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-GGUF-UltraOptimised-DSpark-MTP about 8 hours ago

MLX

#1 opened about 12 hours ago by

huggingfacealthough405

New activity in Solstice-AI/DeepSeek-V4-Flash-Vision-Exp-UltraOptimised-GGUF-DSpark 2 days ago

Running DSpark with llama.cpp

#1 opened 3 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ 3 days ago

What MTP drafter model is this using?

#2 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-6Bit 4 days ago

Questions about the reported throughput (48–74 tok/s @ 256K context) — can't reproduce on M5 Max 128G

#1 opened 4 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-MXFP4-1M 6 days ago

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#1 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4 6 days ago

Production Deployment & Serving Recipes

#2 opened 8 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ-1M 6 days ago

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#2 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4-1M 6 days ago

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#1 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-MXFP4 6 days ago

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#1 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4 6 days ago

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#3 opened 7 days ago by

Exactly what I was hoping for, Thx

#1 opened 9 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ 6 days ago

fix(mtp): restore raw-BF16 MTP head weights (vLLM MTP decoding)

#3 opened 7 days ago by

fix(mtp): restore complete 15-tensor MTP drafter from DavidAU base (BF16, unquantized)

#4 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ-1M 7 days ago

fix(mtp): restore raw-BF16 MTP head weights (vLLM MTP decoding)

#1 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ 7 days ago

感谢您对社区的贡献

#1 opened 7 days ago by

What MTP drafter model is this using?

#2 opened 7 days ago by

感谢您对社区的贡献

#1 opened 7 days ago by

New activity in Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4 8 days ago

Production Deployment & Serving Recipes

#2 opened 8 days ago by