GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
axiomofmind
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
axiomofmind
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
| File | Format | Size | Purpose |
|---|---|---|---|
| Transformers model files | BF16 | 18.82 GB | Original merged weights |
Angry-Claudius-9B-BF16.gguf | BF16 GGUF | 17.92 GB | Unquantized GGUF |
Angry-Claudius-9B-Q8_0.gguf | Q8_0 GGUF | 9.53 GB | High-quality quantization |
Angry-Claudius-9B-Q6_K.gguf | Q6_K GGUF | 7.36 GB | Recommended balance of size and behavior |
python
import torchfrom transformers import AutoProcessor, Qwen3_5ForConditionalGenerationmodel_id = "axiomofmind/Angry-Claudius-9B"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained(model_id,dtype=torch.bfloat16,device_map="auto",)messages = [{"role": "user", "content": "Explain photosynthesis."},]prompt = processor.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=False,)inputs = processor(text=[prompt], return_tensors="pt").to(model.device)with torch.inference_mode():output = model.generate(**inputs,do_sample=False,max_new_tokens=32,)response = processor.batch_decode(output[:, inputs.input_ids.shape[1]:],skip_special_tokens=True,)[0]print(response)
A recent llama.cpp build with Qwen3.5 support is required.
bash
llama-server \-m Angry-Claudius-9B-Q6_K.gguf \--ctx-size 4096 \--flash-attn on \--n-gpu-layers all \--reasoning off \--jinja \--ui
Open http://127.0.0.1:8080 after the server starts.
Recommended generation settings:
| Setting | Value |
|---|---|
| System prompt | Empty |
| Reasoning | Off |
| Temperature | 0 |
| Maximum new tokens | 32 |
This model is based on Qwen/Qwen3.5-9B, released under the Apache 2.0 license.