Oops! Something went wrong
[next-mdx-remote-client] error compiling MDX: Could not parse expression with acorn More information: https://mdxjs.com/docs/troubleshooting-mdx
AI Model2026
Bonsai 2 27B — GGUF
A 27B-class language model packaged in GGUF with end-to-end ternary weights for on-device or single-GPU llama.cpp inference; reduces FP16 footprint to ~5.9–7.2 GB while retaining ~98% of baseline performance and supporting up to 262K tokens.
Introduction
Information
- Websitehuggingface.co
- OrganizationsPrism ML
- Published date2026/09/16
Categories
More Items
AI Model2026
Refines 768P video drafts into 2560×1440 output using MiniMax-H3, latent upscaling, and three diffusion steps. The reported runtime for a 5-second clip is 22.45 seconds on one B200.
AI Model2026
Applies a targeted safety-ablation edit to Liquid AI’s LFM3-1.7B and distributes it in quantized GGUF formats. The model card reports fewer refusals on harmful prompts while retaining the base model’s MMLU score.
AI Model2026
Generates speech from text and can clone a voice from a reference recording without fine-tuning. The 601M-parameter model supports 23 languages, though output quality varies by language.