Ternary Bonsai 27B
PulseAugur coverage of Ternary Bonsai 27B — every cluster mentioning Ternary Bonsai 27B across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
User benchmarks 5 local LLMs on MacBook for practical use · 2 sources tracked
A user has created a custom benchmark system called "Local LLM Arena" to evaluate the performance of five different large language models (LLMs) running locally on their M4 MacBook with 16GB of unified memory. The goal …
-
Bonsai 27B models tested on Terminal-Bench 2.0, 1-bit version unusable
A user tested the Ternary-Bonsai-27B (2-bit) and Bonsai-27B (1-bit) models on the Terminal-Bench 2.0 benchmark, finding that the 2-bit version achieved a score of 7.9%. This performance was lower than the Qwen3.5-9B mod…
-
New ASCIITermDraw Bench tests VLM ability to generate ASCII diagrams
A new benchmark called ASCIITermDraw Bench has been introduced to evaluate the capabilities of Vision-Language Models (VLMs) in generating and editing ASCII art diagrams. Unlike benchmarks focusing on coding or reasonin…
-
Bonsai-27B models integrate with llama.cpp, with updates on binary and ternary support
The Bonsai-27B and Ternary Bonsai-27B models have seen significant updates regarding their integration with the llama.cpp framework. The binary version of Bonsai-27B is now fully supported in upstream llama.cpp across v…