axiomofmind/Angry-Claudius-9B

import torch
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration

model_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)

llama-server \
  -m Angry-Claudius-9B-Q6_K.gguf \
  --ctx-size 4096 \
  --flash-attn on \
  --n-gpu-layers all \
  --reasoning off \
  --jinja \
  --ui