Hugging Face's logo
Wai Chung's picture

Wai Chung PRO

Ternii
dipankarsarkar's profile picture Kugane-123's profile picture faelfernandes's profile picture
·
https://ternii.com

AI & ML interests

None yet

Recent Activity

repliedto their post about 2 hours ago
Published TR Quantisation versions of Qwen3.6-27B, Qwen3.6-35B-A3B and Qwen3.8-Flash-Next: weights packed into trits (2.25-3 per weight), no retraining. - Mac: Qwen3.6-35B-A3B in a 16.5 GB GGUF that fits a 24 GB Mac, ~120 tok/s sustained on an M5 Max. Needs our llama.cpp build (ready-built for macOS and Linux arm64). - vLLM on one DGX Spark: 35B at 180.9 tok/s for 1 user vs 128.0 for NVIDIA's NVFP4, 17.4 vs 21.1 GiB, no significant accuracy difference on the core benchmarks. - Trade-offs on each card: slower prompt processing, lower multilingual maths, and 4-bit GGUF stays closer to the original text. https://huggingface.co/collections/Ternii/tr-quantisation
reacted to theirpost with 🔥 about 14 hours ago
Published TR Quantisation versions of Qwen3.6-27B, Qwen3.6-35B-A3B and Qwen3.8-Flash-Next: weights packed into trits (2.25-3 per weight), no retraining. - Mac: Qwen3.6-35B-A3B in a 16.5 GB GGUF that fits a 24 GB Mac, ~120 tok/s sustained on an M5 Max. Needs our llama.cpp build (ready-built for macOS and Linux arm64). - vLLM on one DGX Spark: 35B at 180.9 tok/s for 1 user vs 128.0 for NVIDIA's NVFP4, 17.4 vs 21.1 GiB, no significant accuracy difference on the core benchmarks. - Trade-offs on each card: slower prompt processing, lower multilingual maths, and 4-bit GGUF stays closer to the original text. https://huggingface.co/collections/Ternii/tr-quantisation
posted an update 2 days ago
Published TR Quantisation versions of Qwen3.6-27B, Qwen3.6-35B-A3B and Qwen3.8-Flash-Next: weights packed into trits (2.25-3 per weight), no retraining. - Mac: Qwen3.6-35B-A3B in a 16.5 GB GGUF that fits a 24 GB Mac, ~120 tok/s sustained on an M5 Max. Needs our llama.cpp build (ready-built for macOS and Linux arm64). - vLLM on one DGX Spark: 35B at 180.9 tok/s for 1 user vs 128.0 for NVIDIA's NVFP4, 17.4 vs 21.1 GiB, no significant accuracy difference on the core benchmarks. - Trade-offs on each card: slower prompt processing, lower multilingual maths, and 4-bit GGUF stays closer to the original text. https://huggingface.co/collections/Ternii/tr-quantisation
View all activity

Organizations

None yet