GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
groxaxo
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
groxaxo
Model Tree
Qwen/Qwen-AgentWorld-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
q/k/v/o + linear-attention input/output projections across all 40 layers),
then merged into the BF16 base weights. The 256 MoE experts were left frozen.A token-balanced blend of cleaned public datasets:
| Source | Focus |
|---|---|
Jackrong/Claude-opus-4.7-TraceInversion-5000x | reasoning / trace-inversion problem solving |
lordx64/reasoning-distill-claude-opus-4-7-max | high-quality reasoning traces |
lordx64/reasoning-distill-opus-4-7-max-sft | instruction-style reasoning SFT |
Infatoshi/kernelbench-mega-traces | GPU-kernel coding traces |
Glint-Research/fable-5-traces | multi-turn agentic coding (tool use) |
All sources were structurally cleaned and quality-filtered before mixing.
python
from transformers import AutoModelForCausalLM, AutoTokenizerm = AutoModelForCausalLM.from_pretrained("groxaxo/Qwento-Agentic", torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)tok = AutoTokenizer.from_pretrained("groxaxo/Qwento-Agentic")
This is a preliminary test checkpoint from a short training run; it has not been
benchmarked and should be treated as experimental. It inherits the license and any usage
restrictions of the base model (Qwen/Qwen-AgentWorld-35B-A3B).