Atoato
PocketLLM

PocketLLM

Verified

Run Qwen3-30B-A3B (MoE) via SGLang on an NVIDIA A6000 — an Ato capsule (Dockerless, host-native, OpenAI-compatible).

4.8(0 reviews)
0Runs
v
GitHub source
OpenGet & Run
PocketLLM screenshot 1
ato install ato/pocketllm

At a glance

  • Run Qwen3-30B-A3B (MoE) via SGLang on an NVIDIA A6000 — an Ato capsule (Dockerless, host-native, OpenAI-compatible).

README

README

ato/pocketllm

Run Qwen3-30B-A3B (MoE) via SGLang on an NVIDIA A6000 — an Ato capsule (Dockerless, host-native, OpenAI-compatible).