-
Bonsai 27B WebGPU Kernels
🌳26Run a 1-bit 27B LLM locally in your browser on WebGPU
-
prism-ml/Ternary-Bonsai-27B-gguf
Text Generation • 4B • Updated • 23 • • 89 -
prism-ml/Bonsai-27B-gguf
Text Generation • 4B • Updated • 513 • 54 -
prism-ml/Ternary-Bonsai-27B-mlx-2bit
Text Generation • 3B • Updated • 6 • 13
AI & ML interests
None defined yet.
Recent Activity
View all activity
Team members 12 private
Organization Card
Concentrating intelligence
Large models can't fit on smartphones.
Datacenters can't sustain them.
PrismML is building ultra dense intelligence to solve both.
-
Bonsai 27B WebGPU Kernels
🌳26Run a 1-bit 27B LLM locally in your browser on WebGPU
-
prism-ml/Ternary-Bonsai-27B-gguf
Text Generation • 4B • Updated • 23 • • 89 -
prism-ml/Bonsai-27B-gguf
Text Generation • 4B • Updated • 513 • 54 -
prism-ml/Ternary-Bonsai-27B-mlx-2bit
Text Generation • 3B • Updated • 6 • 13
models 33
prism-ml/Bonsai-27B-unpacked
27B • Updated • 4 • 4
prism-ml/Ternary-Bonsai-27B-unpacked
27B • Updated • 5 • 4
prism-ml/Bonsai-27B-AWQ-4bit
Image-Text-to-Text • 27B • Updated • 2
prism-ml/Ternary-Bonsai-27B-AWQ-4bit
Image-Text-to-Text • 27B • Updated • 50 • 3
prism-ml/Bonsai-27B-mlx-1bit
Text Generation • 2B • Updated • 23 • 9
prism-ml/Ternary-Bonsai-27B-mlx-2bit
Text Generation • 3B • Updated • 6 • 13
prism-ml/Bonsai-27B-gguf
Text Generation • 4B • Updated • 513 • 54
prism-ml/Ternary-Bonsai-27B-gguf
Text Generation • 4B • Updated • 23 • • 89
prism-ml/Ternary-Bonsai-8B-gguf
Text Generation • 8B • Updated • 16.2k • 110
prism-ml/Ternary-Bonsai-4B-gguf
Text Generation • 4B • Updated • 2.09k • 21
datasets 0
None public yet