GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
WithinUsAI
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
WithinUsAI
Model Tree
google/codegemma-1.1-2b
Input Modalities
Output Modalities
Supported Functionality
The "Reasoner" capabilities of this model are distilled from a multi-source synthetic pipeline focusing on complex coding logic, algorithmic optimization, and step-by-step thinking patterns. The training mixture leverages approximately 100K+ high-quality reasoning examples across five core datasets:
| Dataset Name | Source / Focus | Approx. Size |
|---|---|---|
WithinUsAI/GeminiPro3.2_max_distill_god_seed_25k | High-quality frontier seed prompts for code generation. | ~25k samples |
WithinUsAI/gemini_3.5_flash_distilled_25k | Fast, iterative logical steps and multi-turn debugging data. | ~25k samples |
WithinUsAI/Gemini_3.2_Pro_Distilled | Heavy math logic, structural coding, and system design patterns. | Premium corpus |
WithinUsAI/codegemma_gemini_pro_32_distilled_25k | Target-aligned distillation data optimized for the CodeGemma vocabulary. | ~25k samples |
WithinUsAI/DEEPMIND_Alpha_Distilled | Deep algorithmic competitive programming and math reasoning. | Premium corpus |
vLLM, Ollama, or SGLang.Because CodeGemma utilizes specialized tokens for coding workflows, it's recommended to structure your prompts cleanly to prompt the model's inner chain-of-thought.
python
from transformers import AutoTokenizer, AutoModelForCausalLMimport torchmodel_id = "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype=torch.bfloat16,device_map="auto")# Prompt the model to think step-by-step before delivering codeprompt = """<bos>Analyze the problem and think step-by-step before writing any code.Problem: Write a Python generator function that yields the Fibonacci sequence up to n elements.Answer:"""inputs = tokenizer(prompt, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2)print(tokenizer.decode(outputs[0], skip_special_tokens=True))