GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CoreWorxLab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CoreWorxLab
Model Tree
TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
Input Modalities
Output Modalities
Supported Functionality
bash
vllm serve CoreWorxLab/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-int4-AutoRound \--tensor-parallel-size 1 \--max-model-len 262144 \--gpu-memory-utilization 0.95 \--reasoning-parser qwen3
bash
vllm serve CoreWorxLab/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-int4-AutoRound \--tensor-parallel-size 1 \--max-model-len 262144 \--gpu-memory-utilization 0.95 \--reasoning-parser qwen3 \--speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "CoreWorxLab/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-int4-AutoRound"model = AutoModelForCausalLM.from_pretrained(model_name, dtype="auto")tokenizer = AutoTokenizer.from_pretrained(model_name)
| Parameter | Value |
|---|---|
| Bits | 4 |
| Group size | 128 |
| Symmetric | Yes |
| Calibration | NeelNanda/pile-10k |
| Seq length | 2048 |
Please follow the license of the original model (TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2).