GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SpeedyLabsAI
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
SpeedyLabsAI
Model Tree
Qwen/Qwen3-32B
Input Modalities
Output Modalities
Supported Functionality
step-5, step-10, …).Agentic software engineering: bug fixing, patch generation, and repo navigation
inside a tool-use loop (OpenHands, Aider, mini-swe-agent, or any OpenAI-style
tool-calling harness). It is a thinking model — outputs include reasoning
(reasoning_content / <think>).
bash
vllm serve SpeedyLabsAI/SA-SWE-32B-repro --revision step-10 \--tensor-parallel-size 2 --max-model-len 32768 \--enable-auto-tool-choice --tool-call-parser hermes --reasoning-parser qwen3
python
from openai import OpenAIc = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")print(c.chat.completions.create(model="SpeedyLabsAI/SA-SWE-32B-repro",messages=[{"role":"user","content":"Fix the failing test in ..."}],temperature=0.6, top_p=0.95).choices[0].message.content)
Recommended sampling: temp 0.6, top_p 0.95 (interactive); temp 0 for eval. Needs ~2× 80GB GPU in bf16, or quantize for less.
Full training/serving code, an engineering journal (every failure and fix), and step-by-step runbooks: https://github.com/ranti-iitg/skyrl-swe-repro
bibtex
@misc{skyrl_agent_2025, title={SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent},note={arXiv:2511.16108}, year={2025}}
Base model: Qwen3 (Qwen team). Method: SkyRL-Agent (NovaSky). This is an independent reproduction.