GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
achuthc1298
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
achuthc1298
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
Qwen3_5ForConditionalGeneration (model_type: qwen3_5)Qwen/Qwen3.6-27B (full VLM)r=16, alpha=32, dropout 0.05, continued pre-trainingq_proj, k_proj, v_proj, o_proj, out_proj, gate_proj, up_proj, down_proj (language layers only — vision tower not touched)python
import torchfrom transformers import AutoModelForImageTextToText, AutoProcessorrepo = "achuthc1298/qwen_llm_scs"processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained(repo,dtype=torch.bfloat16,device_map="auto",trust_remote_code=True,attn_implementation="sdpa",)model.eval()# Text-onlymessages = [{"role": "user", "content": [{"type": "text", "text": "Summarize the principle of high-frequency SCS."}]}]inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=400, do_sample=False)print(processor.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))# Vision (figure from a paper)from PIL import Imageimg = Image.open("figure.png").convert("RGB")messages = [{"role": "user", "content": [{"type": "image", "image": img},{"type": "text", "text": "Describe this figure."},]}]inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=400, do_sample=False)print(processor.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Tested on 2× RTX A6000 (48 GB each) with device_map="auto" and per-GPU memory limits of 44 GiB. Total VRAM at inference ≈ 57 GB in BF16.
model.visual.*) is identical to the base model — only the language layers received SCS-domain LoRA updates.qwen3_5 integration in modern transformers; no custom remote code is bundled.Inherits the Qwen license of the base model.