GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
DinoStackAI
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
DinoStackAI
Model Tree
Qwen/Qwen3-Embedding-4B
Input Modalities
Output Modalities
Supported Functionality
python
from sentence_transformers import SentenceTransformermodel = SentenceTransformer("DinoStackAI/Qwen3-Emb-4b-lora-ctx-bioasq-resplit")embeddings = model.encode(["Instruct: ...\nQuery:your query", "document text"])
Or load the base model and adapter explicitly:
python
from sentence_transformers import SentenceTransformermodel = SentenceTransformer("Qwen/Qwen3-Embedding-4B")model.load_adapter("DinoStackAI/Qwen3-Emb-4b-lora-ctx-bioasq-resplit")
python
from vllm import LLMfrom vllm.lora.request import LoRARequestllm = LLM(model="Qwen/Qwen3-Embedding-4B",task="embed",enable_lora=True,max_lora_rank=16,)outputs = llm.embed(["Instruct: ...\nQuery:your query"],lora_request=LoRARequest("bioasq-resplit", 1, "DinoStackAI/Qwen3-Emb-4b-lora-ctx-bioasq-resplit"),)
Qwen/Qwen3-Embedding-4BDinoStackAI/bioasq-rag-13b-resplitr=16, lora_alpha=32, targets q_proj / v_proj)