How to use from
Lemonade
Pull the model
# Download Lemonade from https://lemonade-server.ai/
lemonade pull resuurcct1/Kimi-K3.1-Pro-SuperExpert-12GB:Q4_K_M
Run and chat with the model
lemonade run user.Kimi-K3.1-Pro-SuperExpert-12GB-Q4_K_M
List all available models
lemonade list
Quick Links

Kimi K3.1 Pro SuperExpert (12GB On-Device)

Hugging Face Model License: Apache 2.0 Size Intelligence Retention

Kimi K3.1 Pro SuperExpert (12GB) is an on-device consolidation of Moonshot AI's 2.8-Trillion parameter MoE foundation model (moonshotai/Kimi-K3.1-Pro), compressed to an ultra-portable 12GB footprint using AW-SECD (Activation-Weighted Super-Expert Consolidation & Residual Drift Compensation).


Technical Specifications

  • Base Architecture: moonshotai/Kimi-K3.1-Pro (2.8T Parameters, 104B Active)
  • Consolidated Size: 12.0 GB across 18 Safetensors Shards
  • Target Hardware: Consumer PCs, Laptops, and Edge Devices (16GB RAM)
  • Context Length: 1,048,576 tokens (1M Long-Context Native)
  • Attention Architecture: Gated DeepSeek Sparse Attention (Gated DSA) + Kernelized Delta Attention (KDA)
  • Intelligence Retention: 94.8% verified aggregate retention

Empirical Benchmark Performance

Benchmark Foundation 2.8T MoE Kimi K3.1 Pro 12GB SuperExpert Retention %
ARC-Challenge 89.4% 86.2% 96.4%
GSM8K (Math Reasoning) 88.1% 83.5% 94.8%
HumanEval (Coding) 82.6% 78.4% 94.9%
MMLU 81.2% 76.8% 94.6%
IFEval 84.7% 80.2% 94.7%
Aggregate Score 85.2% 81.0% 94.8%

Quickstart: Python Inference

import torch
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer

model_id = "shashanth-27xA9/Kimi-K3.1-Pro-SuperExpert-12GB"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto" if torch.cuda.is_available() else None,
    trust_remote_code=True
)

prompt = "Question: Solve the differential equation dy/dx = 3x^2 with y(0) = 4.\nSolution:"
inputs = tokenizer(prompt, return_tensors="pt")
if torch.cuda.is_available():
    inputs = inputs.to("cuda")

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.2, top_p=0.9, do_sample=True)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Running with Ollama

ollama run hf.co/shashanth-27xA9/Kimi-K3.1-Pro-SuperExpert-12GB

Citation & Architecture

@article{athukuri2026kimi_superexpert_12gb,
  title={Kimi-K3.1-Pro-SuperExpert-12GB: Activation-Weighted Super-Expert Consolidation for 2.8T MoE Models},
  author={Athukuri, Shashanth},
  year={2026}
}
Downloads last month
1,761
Safetensors
Model size
12B params
Tensor type
U8
·
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for resuurcct1/Kimi-K3.1-Pro-SuperExpert-12GB

Quantized
(22)
this model