cd /news/large-language-models/prismml-releases-bonsai-2-2b-4b-and-… · home › topics › large-language-models › article
[ARTICLE · art-151017] src=huggingface.co ↗ pub= topic=large-language-models verified=true sentiment=· neutral

PrismML Releases Bonsai 2 2B, 4B, and 9B

PrismML released Bonsai 2 in 2B, 4B, and 9B parameter sizes, publishing the models on Hugging Face as GGUF and MLX 2-bit quantized builds under the prism-ml organization. The Ternary-Bonsai-2-9B-gguf build drew 16.4k downloads, while the Ternary-Bonsai-2-4B-gguf and Ternary-Bonsai-2-2B-gguf builds recorded 320 and 249 downloads respectively.

read1 min views1 publishedOct 15, 2026
PrismML Releases Bonsai 2 2B, 4B, and 9B
Image: Hugging Face Blog

Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up prism-ml 's Collections Bonsai 2 Small Bonsai-2 Bonsai 27B Bonsai Image Demos Bonsai Demos Bonsai Image Ternary Bonsai Bonsai Bonsai-Auxiliary Bonsai ONNX Bonsai 2 Small updated about 4 hours ago Upvote 8 Sort: Collection

prism-ml/Ternary-Bonsai-2-9B-gguf
Image-Text-to-Text

• 1B • Updated about 7 hours ago • 16.4k • 14

prism-ml/Ternary-Bonsai-2-9B-mlx-2bit
Image-Text-to-Text

• 9B • Updated 1 day ago • 65 • 2

prism-ml/Ternary-Bonsai-2-4B-gguf
Image-Text-to-Text

• 0.8B • Updated about 7 hours ago • 320 • 8

prism-ml/Ternary-Bonsai-2-4B-mlx-2bit
Image-Text-to-Text

• 5B • Updated about 3 hours ago • 51 • 1

prism-ml/Ternary-Bonsai-2-2B-gguf
Image-Text-to-Text

• 2B • Updated 1 day ago • 249 • 8

prism-ml/Ternary-Bonsai-2-2B-mlx-2bit
Image-Text-to-Text

• 2B • Updated about 3 hours ago • 50 • 1 Upvote 8 +4 Sort: Collection Share collection View history Collection guide Browse collections

source & further reading
huggingface.co — original article Smallwords: controlled-vocabulary generation with one inspectable contract Show HN: An improved kokoro distillation in 9MB Teacher in the Loop: 8M-parameter Kokoro voices in English and Italian, 9 MB int8 ONNX, running in the browser
── more in #large-language-models 4 stories · sorted by recency
── more on @prismml 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/prismml-releases-bon…] indexed:0 read:1min 2026-10-15 · —