GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
lemuralabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
lemuralabs
Model Tree
Jackrong/Qwopus3.6-27B-v2
Input Modalities
Output Modalities
Supported Functionality
Evaluated head-to-head against the base model on identical questions, with an 8192-token budget so step-by-step reasoning is never truncated.
| Benchmark | Base | This model |
|---|---|---|
| MMLU-Pro (350 Q) | 86.86% | 88.29% |
| GSM8K (300 Q) | 98.00% | 97.33% |
| GPQA-Diamond (198 Q) | 57.58% | 57.07% |
Knowledge improved, hard reasoning preserved: +1.43 over base on MMLU-Pro, matching it on GSM8K math and on GPQA-Diamond (graduate-level science, ~frontier-class for a 27B) - with agentic tool-calling added on top.
| Category | Base | This model |
|---|---|---|
| Biology | 96.0% | 94.0% |
| Business | 78.0% | 88.0% |
| Chemistry | 84.0% | 80.0% |
| Computer Science | 84.0% | 84.0% |
| Health | 82.0% | 86.0% |
| Math | 94.0% | 94.0% |
| Physics | 90.0% | 92.0% |
bash
vllm serve lemuralabs/Qwen3.6-27B-Fable-Agentic --trust-remote-code --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --max-model-len 16384
Tip: this model reasons before answering - give it a generous max_tokens so it can finish its chain of thought.
Apache 2.0
| 86.86% |
| 88.29% |