GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
MihaiPopa-1
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
MihaiPopa-1
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
OmniTranslate is a massively multilingual machine translation model supporting over 500 languages. Fine-tuned from Qwen 3 0.6B (with Unsloth), this model is designed for translation tasks on any device!
roșă and ami when translating to Romanian.As it follows, OmniTranslate 1.0 is a experimental model and shouldn't be used for tasks where accurate translations matter.
Providing the ISO code instead of the language name can improve the results a lot.
Code is by Gemini 3 Flash (then some little modifications by myself):
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch# 1. Load from your Hugging Face Repomodel_id = "MihaiPopa-1/OmniTranslate-1.0"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype=torch.float32, # Standard for CPUdevice_map="cpu" # Forces CPU usage)# 2. Translate (replace ron_Latn with your language here)prompt = "<|im_start|>user\nTranslate to ron_Latn: OmniTranslate is a massively multilingual machine translation model supporting over 500 languages!<|im_end|>\n<|im_start|>assistant\n<think>\n"inputs = tokenizer(prompt, return_tensors="pt").to("cpu")with torch.no_grad():outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
I used my own OmniSurgical 1.0, which the dataset itself is a extract of HF's FineTranslations.
120 sentences per language (60 per language pair).
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.