Instructions to use bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ")
config = load_config("bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ"

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": "bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ 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 "bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ"

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 bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ"

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 "bottlecapai/ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ" \
  --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"

ThinkingCap-Qwen3.8-27B-MLX-4bit-DWQ / quant_manifest.json

vojtechba

Name build inputs by folder and file, not by the build machine's paths

d48a1a0 verified 10 days ago

Raw History Blame Contribute Delete

557 Bytes

	{
	"layout": "mixed",
	"calibration": [
	"calib-long/calib.jsonl",
	"calib-n768/calib.jsonl"
	],
	"rows": 2050,
	"window_tokens": 1024,
	"rtn": "probe-rtn/rtn",
	"dwq": {
	"num_samples": 2018,
	"max_seq_length": 1024,
	"batch_size": 4,
	"learning_rate": 2e-07,
	"grad_checkpoint": true,
	"data": "own transcripts"
	},
	"modules": {
	"4bit": 168,
	"8bit": 241,
	"bf16": 528
	},
	"mtp": {
	"embedded": true,
	"bits": 8
	},
	"vision": {
	"embedded": true,
	"tensors": 333
	},
	"bytes": 22536644064
	}