GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
beyoru
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
beyoru
Model Tree
Qwen/Qwen3.5-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
This model is trained to maintain context across multiple tool interactions, rather than treating each tool call as an isolated operation. This makes it suitable for workflows where the result of one action determines the next action.
The model is trained on trajectories containing tool selection and execution, allowing it to reason about:
The training data contains high-effort reasoning trajectorie
top_p = 0.20, ~7.5 of 256 experts per layerpython
from transformers import AutoTokenizer, AutoModelForCausalLMtk = AutoTokenizer.from_pretrained("beyoru/Clawd-Agent")model = AutoModelForCausalLM.from_pretrained("beyoru/Clawd-Agent", dtype="auto", device_map="auto")msgs = [{"role": "user", "content": "..."}]ids = tk.apply_chat_template(msgs, tools=TOOLS, add_generation_prompt=True, return_tensors="pt")
Serving with vLLM:
bash
vllm serve beyoru/Clawd-Agent --max-model-len 8192
The chat template emits <think>\n in the generation prompt, so the model continues the
reasoning block and closes it with </think> before the answer.
Inherits the base model's MIT license. Fine-tuned on a narrow task distribution — evaluate on your own workload before relying on it for anything outside multi-turn tool use.