GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pearl-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
pearl-ai
Model Tree
Qwen/Qwen3-30B-A3B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-30B-A3B-Instruct-2507 (Mixture-of-Experts)Qwen3MoeForCausalLMminer/vllm-miner)MMLU-Pro (full test split, 12,032 questions), generative 5-shot CoT, run with the Qwen3-30B-A3B-Instruct-2507 sampling recipe (
text
temperature=0.7, top_p=0.8, top_k=20, min_p=0| Model | MMLU-Pro |
|---|---|
| Original | 77.88% |
| Pearl | 77.33% |
This model is intended to be served through the Pearl miner stack, where vLLM inference is integrated with Pearl mining workflows.
Typical flow:
pearld with RPC enabled.Follow the miner setup from the Pearl repo:
High-level prerequisites:
uvpearld node with RPC credentialsFrom the Pearl repository root:
bash
docker buildx build -t vllm_miner . -f miner/vllm-miner/Dockerfilebash
docker run --rm -it --gpus all \ -p 8000:8000 -p 8337:8337 -p 8339:8339 \ -e PEARLD_RPC_URL=<PEARLD_URL> \ -e PEARLD_RPC_USER=<RPC_USER> \ -e PEARLD_RPC_PASSWORD=<RPC_PASSWORD> \ -e VLLM_USE_DEEP_GEMM=0 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --shm-size 8g \ vllm_miner:latest \ pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl \ --host 0.0.0.0 --port 8000 \ --max-model-len 8192 \ --gpu-memory-utilization 0.9 \ --enforce-eagerbash
pip install vllm vllm serve "pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl"bash
curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'python
from transformers import pipeline pipe = pipeline("text-generation", model="pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl")messages = [ {"role": "user", "content": "Who are you?"},]pipe(messages)python
from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl")model = AutoModelForCausalLM.from_pretrained("pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl") messages = [ {"role": "user", "content": "Who are you?"},]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)outputs = model.generate(**inputs, max_new_tokens=40)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))This model is based on Qwen3 and is distributed under the Apache 2.0 license.
docker buildx build -t vllm_miner . -f miner/vllm-miner/Dockerfiledocker run --rm -it --gpus all \ -p 8000:8000 -p 8337:8337 -p 8339:8339 \ -e PEARLD_RPC_URL=<PEARLD_URL> \ -e PEARLD_RPC_USER=<RPC_USER> \ -e PEARLD_RPC_PASSWORD=<RPC_PASSWORD> \ -e VLLM_USE_DEEP_GEMM=0 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --shm-size 8g \ vllm_miner:latest \ pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl \ --host 0.0.0.0 --port 8000 \ --max-model-len 8192 \ --gpu-memory-utilization 0.9 \ --enforce-eagerpip install vllm vllm serve "pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl"curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'from transformers import pipeline pipe = pipeline("text-generation", model="pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl")messages = [ {"role": "user", "content": "Who are you?"},]pipe(messages)from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl")model = AutoModelForCausalLM.from_pretrained("pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl") messages = [ {"role": "user", "content": "Who are you?"},]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)outputs = model.generate(**inputs, max_new_tokens=40)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))