Instructions to use hermitdave/BigBang-v1-MLX-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hermitdave/BigBang-v1-MLX-Q4_K_M 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("hermitdave/BigBang-v1-MLX-Q4_K_M")

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 hermitdave/BigBang-v1-MLX-Q4_K_M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "hermitdave/BigBang-v1-MLX-Q4_K_M"

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": "hermitdave/BigBang-v1-MLX-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use hermitdave/BigBang-v1-MLX-Q4_K_M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "hermitdave/BigBang-v1-MLX-Q4_K_M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "hermitdave/BigBang-v1-MLX-Q4_K_M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "hermitdave/BigBang-v1-MLX-Q4_K_M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use hermitdave/BigBang-v1-MLX-Q4_K_M 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 "hermitdave/BigBang-v1-MLX-Q4_K_M"

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 hermitdave/BigBang-v1-MLX-Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hermitdave/BigBang-v1-MLX-Q4_K_M with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "hermitdave/BigBang-v1-MLX-Q4_K_M"

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 "hermitdave/BigBang-v1-MLX-Q4_K_M" \
  --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"

BigBang-v1-MLX-Q4_K_M

This model was converted to MLX format from endless-frontier/BigBang-v1 using mlx_lm version 0.31.3.

Quantization: mixed_4_6 (equivalent to llama.cpp Q4_K_M). 4-bit base with higher bits applied to first/last 1/8 of layers, every 3rd layer, v_proj/down_proj, and lm_head.

Use with mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/BigBang-v1-MLX-Q4_K_M")

messages = [{"role": "user", "content": "Hello!"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
response = generate(model, tokenizer, prompt=prompt, max_tokens=512)

Or via CLI:

python3 -m mlx_lm.chat --model mlx-community/BigBang-v1-MLX-Q4_K_M

Model Info

Architecture: qwen3_5_moe — 35B total, 3B active, 256 experts (8/tok)
Attention: Hybrid linear + full attention
Context: 262K tokens
Type: Text-only (language model)

Variants

Repo	Quantization	Size	Use Case
BigBang-v1-MLX-4bit	uniform 4-bit	~19.5 GB	Maximum speed
BigBang-v1-MLX-Q4_K_M	mixed_4_6	~21.0 GB	Best quality/speed tradeoff
BigBang-v1-MLX-VLM-4bit	uniform 4-bit	~20.4 GB	Multimodal, fast
BigBang-v1-MLX-VLM-Q4_K_M	mixed_4_6	~22.0 GB	Multimodal, quality