GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
orwelian84
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
orwelian84
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
Matched baseline-versus-derivative benchmarking is in progress. The public text matrix covers GPQA Diamond, IFBench, and LiveCodeBench v6. It also includes matched perplexity and refusal controls. Every active task uses exact, executable, or otherwise deterministic scoring. HLE is excluded because the reported setup uses a paid model judge. Results will be added with exact harness versions, task revisions, prompts, sample counts, and raw result files.
The Qwen model card also reports several private or environment-heavy agent benchmarks. Those results cannot be reproduced from model weights alone. They will remain clearly marked as untested unless the exact datasets and harnesses become available.
These small diagnostics come from OBLITERATUS itself. They are not substitutes for the matched benchmark matrix.
| Diagnostic | Result |
|---|---|
| Perplexity | 3.5903 |
| Coherence check | 1.0 |
| Capability checks | 5 of 6 |
| Refusal rate | 20% of 30 sampled prompts |
| First-token KL divergence | 1.2249 |
| Spectral certificate | RED |
The high KL divergence and red spectral result indicate substantial behavior change. Evaluate the model for each intended use before deployment.
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0c1a12752910167543bd7a6135e05a8bace99901e64bfda09fd62eb75ae103c886154c8171608b79e1c2de6416f739dedcbd4e8a4The run kept all 1,184 parameters on one RTX PRO 6000 in BF16. It used Flash Attention 2 and did not use CPU, disk, multi-GPU, or model offload.
You are responsible for suitable safeguards, evaluation, and compliance in the environment where you run the model.
Use current Qwen3.8-compatible versions of Transformers, vLLM, or SGLang. For example:
bash
vllm serve orwelian84/Qwen3.8-27B-OBLITERATUS-Advanced \--dtype bfloat16 \--max-model-len 65536
Qwen3.8 uses thinking mode by default. Follow the official Qwen3.8 model card for chat-template and sampling guidance.
The repository includes a sanitized derivation manifest and SHA-256 records. The run preserved the original failed compatibility attempt separately. The published model comes only from the fresh validated retry.
The base model is Apache 2.0 licensed. See LICENSE and the
Qwen/Qwen3.8-27B model card.
The ablation tool is
elder-plinius/OBLITERATUS.