Instructions to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("richardyoung/Kimi-K2-Instruct-0905-MLX-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default richardyoung/Kimi-K2-Instruct-0905-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use richardyoung/Kimi-K2-Instruct-0905-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "richardyoung/Kimi-K2-Instruct-0905-MLX-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

richardyoung commited on Nov 26, 2025

Commit

bed36e8

verified ·

1 Parent(s): 5072e5d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +34 -1

README.md CHANGED Viewed

@@ -52,7 +52,40 @@ This is a **high-performance 4-bit quantized version** of Kimi K2 Instruct, opti
 ## 🎯 Quick Start
-### Installation
 ```bash
 pip install mlx-lm

 ## 🎯 Quick Start
+#
+## Hardware Requirements
+Kimi-K2 is a massive 671B parameter MoE model. Choose your quantization based on available unified memory:
+| Quantization | Model Size | Min RAM | Quality |
+|:------------:|:----------:|:-------:|:--------|
+| **2-bit** | ~84 GB | 96 GB | Acceptable - some quality loss |
+| **3-bit** | ~126 GB | 128 GB | Good - recommended minimum |
+| **4-bit** | ~168 GB | 192 GB | Very Good - best quality/size balance |
+| **5-bit** | ~210 GB | 256 GB | Excellent |
+| **6-bit** | ~252 GB | 288 GB | Near original |
+| **8-bit** | ~336 GB | 384 GB | Original quality |
+### Recommended Configurations
+| Mac Model | Max RAM | Recommended Quantization |
+|:----------|:-------:|:-------------------------|
+| Mac Studio M2 Ultra | 192 GB | 4-bit |
+| Mac Studio M4 Ultra | 512 GB | 8-bit |
+| Mac Pro M2 Ultra | 192 GB | 4-bit |
+| MacBook Pro M3 Max | 128 GB | 3-bit |
+| MacBook Pro M4 Max | 128 GB | 3-bit |
+### Performance Notes
+- **Inference Speed**: Expect ~5-15 tokens/sec depending on quantization and hardware
+- **First Token Latency**: 10-30 seconds for model loading
+- **Context Window**: Full 128K context supported
+- **Active Parameters**: Only ~37B parameters active per token (MoE architecture)
+## Installation
 ```bash
 pip install mlx-lm