KiteFish-I1-10B

KiteFish-I1-10B is a compact, efficient casual language model by KiteFishAI, designed for low-latency inference on consumer hardware with strong reasoning and agentic capabilities.

Model Details

Property	Value
Model type	KiteFishForCausalLM
Parameters	~11.4B
Architecture	Mixture-of-Experts (MoE)
VRAM required	~8GB
Context length	131K tokens
License	Apache 2.0

Capabilities

• Configurable reasoning effort (low / medium / high)
• Full chain-of-thought support
• Function calling and structured outputs
• Web browsing and Python code execution (agentic)
• Multilingual support

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "KiteFishAI/KiteFish-I1-10B",
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "KiteFishAI/KiteFish-I1-10B",
    trust_remote_code=True,
)

inputs = tokenizer("Hello! What can you do?", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ollama

ollama pull KiteFishAI/KiteFish-I1-10B
ollama run KiteFishAI/KiteFish-I1-10B

License

Apache 2.0 — free to use, modify, and distribute commercially.

---

Built by KiteFishAI