GreenBitAI/Terza-27B-Agent-gbx
Image-Text-to-Text • 27B • Updated • 42 • 1
AI & ML interests
Low-bit neural networks, Edge AI, sustainable ML
Recent Activity
View all activity
yanghaojin
updated a
model 4 days ago
yanghaojin
published a
model 4 days ago
yanghaojin
posted an update 4 days ago
Post
2,775
Fish Audio’s Drama 3 text-to-speech now runs locally on Apple silicon and DGX Spark with gbx-lm. 🎙️
GreenBitAI/Drama-3-8bit-paged
Real time on 64 GB Macs and up (2.6x), and it still runs on a 48 GB MacBook Pro: experts stream from the SSD
Zero-shot voice cloning from a 5–30 s clip, and the cloned voice can speak other languages
Multi-speaker dialogue, cues like [laughs] [whispering], 83 languages
OpenAI-compatible /v1/audio/speech with streaming, no PyTorch needed
Built with Fish Audio · community build · Fish Audio Community License
GreenBitAI/Drama-3-8bit-paged
Real time on 64 GB Macs and up (2.6x), and it still runs on a 48 GB MacBook Pro: experts stream from the SSD
Zero-shot voice cloning from a 5–30 s clip, and the cloned voice can speak other languages
Multi-speaker dialogue, cues like [laughs] [whispering], 83 languages
OpenAI-compatible /v1/audio/speech with streaming, no PyTorch needed
Built with Fish Audio · community build · Fish Audio Community License
yanghaojin
updated a
model 4 days ago
yanghaojin
updated a
collection 4 days ago
NicoNico
updated a
model 5 days ago
yanghaojin
updated a
collection 5 days ago
yanghaojin
published a
model 5 days ago
yanghaojin
updated a
Space 6 days ago
yanghaojin
updated 5
models 6 days ago
GreenBitAI/Ternary-Bonsai-2-27B-gbx
Image-Text-to-Text • 27B • Updated • 446 • 2
GreenBitAI/Qwen3.8-27B-4bit
Image-Text-to-Text • 27B • Updated • 293
GreenBitAI/Qwen3.8-Flash-Next-4bit-paged
Image-Text-to-Text • 5B • Updated • 842
GreenBitAI/Qwen3.6-35B-A3B-8bit-paged
Image-Text-to-Text • 3B • Updated • 476
GreenBitAI/Qwen3.6-35B-A3B-4bit-paged
Image-Text-to-Text • 3B • Updated • 286
yanghaojin
updated a
collection 10 days ago
yanghaojin
posted an update 10 days ago
Post
2,045
Ternary Bonsai 2 27B: 2.7× faster on a Mac, 5.9 GB on DGX Spark ⚡
gbx v0.8.2:
• 114 tok/s on M3 Ultra, 2.7× the official MLX runtime
• 62 tok/s on DGX Spark, 2.1× llama.cpp
• 27B in 5.9 GB of memory
Weights are just −1, 0, +1.
GreenBit Ternary Models, coming soon.
🤗 Model: GreenBitAI/Ternary-Bonsai-2-27B-gbx
⚙️ gbx: https://github.com/GreenBitAI/gbx-lm/releases/tag/v0.8.2
gbx v0.8.2:
• 114 tok/s on M3 Ultra, 2.7× the official MLX runtime
• 62 tok/s on DGX Spark, 2.1× llama.cpp
• 27B in 5.9 GB of memory
Weights are just −1, 0, +1.
GreenBit Ternary Models, coming soon.
🤗 Model: GreenBitAI/Ternary-Bonsai-2-27B-gbx
⚙️ gbx: https://github.com/GreenBitAI/gbx-lm/releases/tag/v0.8.2
yanghaojin
published a
model 10 days ago
yanghaojin
posted an update 14 days ago
Post
5,609
DeepSeek-V4.1-Flash-1017, running locally on a Mac
Our 4-bit paged build is up: GreenBitAI/DeepSeek-V4.1-Flash-1017-4bit-paged
On one M3 Ultra Mac Studio with gbx:
• ~22 tok/s standard decode
• ~44 tok/s on code with DeepSeek's official draft head (1.99×)
• ~33 tok/s on chat with the draft head
Why run 1017: DeepSeek reports 77.0 on DeepSWE v1.1 (up from 74.2) and 42.3 on Terminal-Bench 4.0 (up from 31.2), with shorter outputs (https://api-docs.deepseek.com/news/news261017).
It reads text and images, and plugs straight into Claude Code and Codex; the setup is in the model card. The paged format also loads on Macs with less memory, and on an NVIDIA DGX Spark with experts paged from the SSD;
Engine: https://github.com/GreenBitAI/gbx-lm/releases
Our 4-bit paged build is up: GreenBitAI/DeepSeek-V4.1-Flash-1017-4bit-paged
On one M3 Ultra Mac Studio with gbx:
• ~22 tok/s standard decode
• ~44 tok/s on code with DeepSeek's official draft head (1.99×)
• ~33 tok/s on chat with the draft head
Why run 1017: DeepSeek reports 77.0 on DeepSWE v1.1 (up from 74.2) and 42.3 on Terminal-Bench 4.0 (up from 31.2), with shorter outputs (https://api-docs.deepseek.com/news/news261017).
It reads text and images, and plugs straight into Claude Code and Codex; the setup is in the model card. The paged format also loads on Macs with less memory, and on an NVIDIA DGX Spark with experts paged from the SSD;
Engine: https://github.com/GreenBitAI/gbx-lm/releases
yanghaojin
updated a
collection 14 days ago
yanghaojin
updated a
model 14 days ago