Instructions to use inferencerlabs/DeepSeek-V4-Flash-MLX-9bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/DeepSeek-V4-Flash-MLX-9bit 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("inferencerlabs/DeepSeek-V4-Flash-MLX-9bit")

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 inferencerlabs/DeepSeek-V4-Flash-MLX-9bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use inferencerlabs/DeepSeek-V4-Flash-MLX-9bit 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 "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit"

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 inferencerlabs/DeepSeek-V4-Flash-MLX-9bit

Run Hermes

hermes

MLX LM

How to use inferencerlabs/DeepSeek-V4-Flash-MLX-9bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "inferencerlabs/DeepSeek-V4-Flash-MLX-9bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

DeepSeek-V4-Flash

See DeepSeek-V4-Flash in action: demonstration videos

For improved performance, download and enable a compatible MTP speculative decoder.

Tested on an M3 Ultra 512 GiB RAM using Inferencer app v1.11.7

Text inference	~31 tokens/s @ 1000 tokens ~148.5 GiB
Text inference (with MTP)	~37.3 tokens/s @ 1000 tokens ~152.9 GiB

Q9 typically achieves near lossless accuracy in our coding test

In this build, the 4-bit pre-quantized weights of the base model were repacked (rather than dequantized and re-quantized to 9-bit), as this approach performed slightly better in our initial coding tests. All remaining weights were quantized to 9-bit.

Quantized with a modified version of MLX

For more details see our demonstration videos or visit DeepSeek-V4-Flash.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.

Downloads last month: 4,348

Safetensors

Model size

284B params

Tensor type

BF16

U32

F32

I64

MLX

Hardware compatibility

Quantized

Model tree for inferencerlabs/DeepSeek-V4-Flash-MLX-9bit

Base model

deepseek-ai/DeepSeek-V4-Flash

Quantized

(68)

this model