metadata

base_model: second-state/Qwen3-30B-A3B-GGUF
license: other
license_name: qwen-research
license_link: https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/LICENSE
model_creator: Qwen
model_name: Qwen3-30B-A3B
quantized_by: Second State Inc.

Qwen3-30B-A3B-GGUF

Original Model

second-state/Qwen3-30B-A3B-GGUF

Run with LlamaEdge

LlamaEdge version:
- Thinking: v0.17.0 and above
- No Thinking: v0.18.2

Prompt template

Prompt type: chatml (for thinking)

Prompt string

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Prompt type: qwen3-no-think (for no thinking)

Prompt string

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message_1}<|im_end|>
<|im_start|>assistant
{assistant_message_1}<|im_end|>
<|im_start|>user
{user_message_2}<|im_end|>
<|im_start|>assistant
<think>

</think>

Context size: 128000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-30B-A3B-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name Qwen3-30B-A3B \
  --prompt-template chatml \
  --ctx-size 128000

Quantized with llama.cpp b5097