GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Momix-44
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Momix-44
Model Tree
samuelcardillo/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled
Input Modalities
Output Modalities
Supported Functionality
You can use this model in your applications by loading it with Hugging Face's transformers library:
python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfigimport torchimport osimport signalimport randomimport numpy as npimport timeimport sysif ("PYTORCH_ALLOC_CONF" not in os.environand "PYTORCH_CUDA_ALLOC_CONF" not in os.environ):print(f"PYTORCH_ALLOC_CONF.")os.environ["PYTORCH_ALLOC_CONF"] = "expandable_segments:True"cpu_count = os.cpu_count()print(f"Number of CPU cores in the system: {cpu_count}")half_cpu_count = cpu_count // 2os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)torch.set_num_threads(half_cpu_count)print(f"PyTorch threads: {torch.get_num_threads()}")print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")# Load the model and tokenizerOLD_MODEL_ID = "huihui-ai/Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated"sys.path.append(OLD_MODEL_ID)print(f"Load Model {OLD_MODEL_ID} ... ")quant_config_4 = BitsAndBytesConfig(load_in_4bit=True,bnb_4bit_compute_dtype=torch.bfloat16,bnb_4bit_use_double_quant=True,llm_int8_enable_fp32_cpu_offload=True,)model = AutoModelForCausalLM.from_pretrained(OLD_MODEL_ID,device_map="auto",trust_remote_code=True,torch_dtype="auto",low_cpu_mem_usage=True,#quantization_config=quant_config_4,#attn_implementation="flash_attention_2")tokenizer = AutoTokenizer.from_pretrained(OLD_MODEL_ID, trust_remote_code=True)messages = []skip_prompt=Trueskip_special_tokens=Trueclass CustomTextStreamer(TextStreamer):def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)self.generated_text = ""self.stop_flag = Falseself.init_time = time.time() # Record initialization timeself.end_time = None # To store end timeself.first_token_time = None # To store first token generation timeself.think_tokens_count = 0 # To track total think tokensself.token_count = 0 # To track total tokensdef on_finalized_text(self, text: str, stream_end: bool = False):if self.first_token_time is None and text.strip(): # Set first token time on first non-empty textself.first_token_time = time.time()self.generated_text += textself.token_count += 1if self.think_tokens_count == 0 and "</think>" in self.generated_text:self.think_tokens_count = self.token_countprint(text, end="", flush=True)if stream_end:self.end_time = time.time() # Record end time when streaming endsif self.stop_flag:raise StopIterationdef stop_generation(self):self.stop_flag = Trueself.end_time = time.time() # Record end time when generation is stoppeddef get_metrics(self):"""Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""if self.end_time is None:self.end_time = time.time() # Set end time if not already settotal_time = self.end_time - self.init_time # Total time from init to endtokens_per_second = self.token_count / total_time if total_time > 0 else 0first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else Nonemetrics = {"init_time": self.init_time,"first_token_time": self.first_token_time,"first_token_latency": first_token_latency,"end_time": self.end_time,"total_time": total_time, # Total time in seconds"think_tokens_count": self.think_tokens_count,"total_tokens": self.token_count,"tokens_per_second": tokens_per_second}return metricsdef generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, max_new_tokens):text = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,)model_inputs = tokenizer([text],return_tensors="pt",).to(model.device)streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)def signal_handler(sig, frame):streamer.stop_generation()print("\n[Generation stopped by user with Ctrl+C]")signal.signal(signal.SIGINT, signal_handler)print("Response: ", end="", flush=True)try:generated_ids = model.generate(**model_inputs,#use_cache=False,#pad_token_id=tokenizer.eos_token_id,max_new_tokens = max_new_tokens,streamer=streamer,)del generated_idsexcept StopIteration:print("\n[Stopped by user]")del model_inputstorch.cuda.empty_cache()signal.signal(signal.SIGINT, signal.SIG_DFL)return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()while True:print(f"skip_prompt: {skip_prompt}")print(f"skip_special_tokens: {skip_special_tokens}")user_input = input("User: ").strip()if user_input.lower() == "/exit":print("Exiting chat.")breakif user_input.lower() == "/clear":messages = []print("Chat history cleared. Starting a new conversation.")continueif user_input.lower() == "/skip_prompt":skip_prompt = not skip_promptcontinueif user_input.lower() == "/skip_special_tokens":skip_special_tokens = not skip_special_tokenscontinueif not user_input:print("Input cannot be empty. Please enter something.")continuemessages.append({"role": "user","content": user_input})response, stop_flag, metrics = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, 40960)print("\n\nMetrics:")for key, value in metrics.items():print(f" {key}: {value}")print("", flush=True)if stop_flag:continuemessages.append({"role": "assistant","content": response.strip()})
Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
markdown
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge