Open LLMs with a built-in System 1: decisions in one forward pass from the KV cache, served by vLLM. pip install "plumbify[vllm]"
The Totum Labs
non-profit
AI & ML interests
None defined yet.
Recent Activity
models 6
totum-labs/Qwen3.5-35B-A3B-plumb
Text Generation • 36B • Updated • 429
totum-labs/Qwen3.5-27B-plumb
Text Generation • 28B • Updated • 437 • 1
totum-labs/gemma-4-12B-it-plumb
Text Generation • 12B • Updated • 431 • 1
totum-labs/Qwen3.5-9B-plumb
Text Generation • 10B • Updated • 433 • 1
totum-labs/Qwen3.5-4B-plumb
Text Generation • 5B • Updated • 423
totum-labs/Qwen3-1.7B-plumb
Text Generation • 2B • Updated • 412