Instructions to use pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit 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("pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit")
config = load_config("pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit")

# 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 pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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 "pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit"

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": "pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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 "pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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 pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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 "pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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 "pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-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"

pipenetwork commited on 9 days ago

Commit

fcc2061

verified ·

1 Parent(s): a534b27

Correct norm-comparison wording; link conversion tooling

Browse files

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ We verified the identity numerically rather than assuming it:
 | Check | Result |
 |---|---|
 | `lm_head.weight` (BF16 in both) vs GGUF `output.weight` | **bit-exact**, 0 mismatches across 262,144 values |
-| RMSNorm weights (`input_layernorm`, `q_norm`, `post_attention_layernorm`, final `norm`) | **bit-exact** under llama.cpp's `w → w + 1` storage convention |
 | `embed_tokens` vs GGUF Q8_0 `token_embd` | cosine 0.999956 — consistent with a plain Q8_0 round-trip |
 So these MLX quants are made from the original bf16 weights, **not** by dequantizing a GGUF. There is no GGUF round-trip loss.
@@ -99,8 +99,8 @@ print(generate(model, processor, prompt, ["your_image.jpg"], max_tokens=512, ver
 | Repo | Bits | Size |
 |---|---|---|
 | [...-MLX-4bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit) | 4 | 6.0 GB |
-| [...-MLX-6bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-6bit) | 6 | 8.2 GB |
-| [...-MLX-8bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-8bit) | 8 | 10.4 GB |
 | [...-MLX-bf16](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-bf16) | 16 | 18.8 GB |
 Group size 64, `affine` mode. The vision tower is left unquantized (mlx-vlm's default for multimodal projector/patch-embed modules), so the size delta between tiers comes from the language model.
@@ -129,6 +129,10 @@ mxfp8     0.571, 0.719, 0.895, 0.683, 0.426, 0.770, 0.671
 These are not measurements of these MLX repos — treat them as characterising the weights, not this quantization.
 ## License
 Apache 2.0, inherited from Qwen3.5-9B.

 | Check | Result |
 |---|---|
 | `lm_head.weight` (BF16 in both) vs GGUF `output.weight` | **bit-exact**, 0 mismatches across 262,144 values |
+| RMSNorm weights (`input_layernorm`, `q_norm`, `post_attention_layernorm`, final `norm`) | equal `source + 1.0` under llama.cpp's shift convention (12542/12544 elements exact; 2 differ by 1 ULP from the float32 addition) |
 | `embed_tokens` vs GGUF Q8_0 `token_embd` | cosine 0.999956 — consistent with a plain Q8_0 round-trip |
 So these MLX quants are made from the original bf16 weights, **not** by dequantizing a GGUF. There is no GGUF round-trip loss.
 | Repo | Bits | Size |
 |---|---|---|
 | [...-MLX-4bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-4bit) | 4 | 6.0 GB |
+| [...-MLX-6bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-6bit) | 6 | 7.7 GB |
+| [...-MLX-8bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-8bit) | 8 | 9.7 GB |
 | [...-MLX-bf16](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-bf16) | 16 | 18.8 GB |
 Group size 64, `affine` mode. The vision tower is left unquantized (mlx-vlm's default for multimodal projector/patch-embed modules), so the size delta between tiers comes from the language model.
 These are not measurements of these MLX repos — treat them as characterising the weights, not this quantization.
+## Conversion tooling
+Scripts and the provenance proof: [github.com/PipeNetwork/defiant-fable-mlx](https://github.com/PipeNetwork/defiant-fable-mlx)
 ## License
 Apache 2.0, inherited from Qwen3.5-9B.