Skip to content
omgitsbase / llmashView on GitHub
Ollama-compatible LLM server. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and beats ollama by much 2-4x. Made possible with custom CUDA kernels, MTP, speculation and its own 3-bit builds. Uncensors models in one command. Windows and Linux, NVIDIA. Optimized to not eat up ram.
☆37Nov 12, 2026Updated last week

Alternatives and similar repositories for llmash

Users that are interested in llmash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?