All Reviews (8)
Ternary Bonsai
Open Source ModelsReviewed 2026-04-17
1.58-bit LLMs that fit in 1.75 GB — runs in your browser via WebGPU
No community votes yet
Just Added
Bonsai (PrismML)
Open Source ModelsReviewed 2026-04-08
First commercially licensed 1-bit LLMs — 8B in 1.15 GB, 8x faster on-device
No community votes yet
Tiny Aya
Open Source ModelsReviewed 2026-04-05
3B-parameter open model supporting 70+ languages — runs offline on a phone
No community votes yet
Bonsai-8B
Open Source ModelsReviewed 2026-04-05
1-bit quantized 8B LLM — 1.15GB, runs on-device at 368 tok/s
No community votes yet
Gemma 4
Open Source ModelsReviewed 2026-04-04
Google's open multimodal model that runs on your GPU and beats closed rivals
No community votes yet
Llama 4 (Scout + Maverick)
Open Source ModelsReviewed 2026-04-04
Meta's first open-weight multimodal MoE models — 10M context, vision-native
No community votes yet
Google Gemma 4
Open Source ModelsReviewed 2026-04-03
Google's first Apache 2.0 open model family with native multimodal
No community votes yet
Trinity-Large-Thinking
Open Source ModelsReviewed 2026-04-03
399B open MoE reasoning model that's 96% cheaper than Claude Opus
No community votes yet