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 8 days ago

Commit

15f8b33

verified ·

1 Parent(s): fb05bcd

Add 5bit tier to the measured quantization comparison

Browse files

Files changed (1) hide show

README.md +11 -9

README.md CHANGED Viewed

@@ -100,6 +100,7 @@ print(generate(model, processor, prompt, ["your_image.jpg"], max_tokens=512, ver
 |---|---|---|
 | [...-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 |
@@ -113,26 +114,27 @@ against bf16's own output distribution, so lower means closer to the original mo
 | model | lang. weights | ppl | Δppl | KL(bf16‖quant) | top-1 vs bf16 | decode |
 |---|---|---|---|---|---|---|
-| bf16 reference | 17.91 GB | 8.1273 | — | — | — | 38.9 t/s |
-| 8bit | 9.51 GB | 8.1277 | +0.00% | 0.00124 | 98.24% | 67.3 t/s |
-| 6bit | 7.28 GB | 8.1426 | +0.19% | 0.00523 | 96.20% | 80.4 t/s |
-| **4bit** (this repo) | 5.04 GB | 8.5816 | +5.59% | 0.07330 | 87.06% | 109.1 t/s |
-| [nightmedia mxfp4](https://huggingface.co/nightmedia/Qwen3.5-9B-DS9-USS-Defiant-mxfp4-mlx) | 4.76 GB | 8.9443 | +10.05% | 0.11328 | 82.34% | 113.8 t/s |
 Reading it:
 - **8bit is effectively free** — bf16 perplexity to four decimals at 47% of the footprint
   and 1.7x the decode speed.
-- **6bit is the value pick** at +0.19%.
-- **The quality cliff is 6bit → 4bit**, not further down: KL jumps 14x. If you can fit
-  7.3 GB, prefer 6bit over 4bit.
 - At the 4-bit tier this affine group-64 quant loses about half the perplexity MXFP4 does,
   costing 4.5 vs 4.25 bits/weight (~6% more storage, ~4% slower decode).
 All tiers are quantizations of the same weights, so this isolates the quantization scheme.
 Reproduce with [`bench.py`](https://github.com/PipeNetwork/defiant-fable-mlx).
-## Sampling
 DavidAU's notes for this model, which carry over:

 |---|---|---|
 | [...-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-5bit](https://huggingface.co/pipenetwork/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-5bit) | 5 | 6.6 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 |
 | model | lang. weights | ppl | Δppl | KL(bf16‖quant) | top-1 vs bf16 | decode |
 |---|---|---|---|---|---|---|
+| bf16 reference | 17.91 GB | 8.1273 | — | — | — | 39.2 t/s |
+| 8bit | 9.51 GB | 8.1277 | +0.00% | 0.00124 | 98.24% | 67.9 t/s |
+| 6bit | 7.28 GB | 8.1426 | +0.19% | 0.00523 | 96.20% | 80.9 t/s |
+| 5bit | 6.16 GB | 8.2012 | +0.91% | 0.01845 | 93.24% | 92.5 t/s |
+| **4bit** (this repo) | 5.04 GB | 8.5816 | +5.59% | 0.07330 | 87.06% | 110.0 t/s |
+| [nightmedia mxfp4](https://huggingface.co/nightmedia/Qwen3.5-9B-DS9-USS-Defiant-mxfp4-mlx) | 4.76 GB | 8.9443 | +10.05% | 0.11328 | 82.34% | 114.7 t/s |
 Reading it:
 - **8bit is effectively free** — bf16 perplexity to four decimals at 47% of the footprint
   and 1.7x the decode speed.
+- **5bit is the best quality-per-GB**: under 1% perplexity for 6.2 GB.
+- **The cliff is 5bit → 4bit**, where KL jumps 4x and perplexity goes +0.91% → +5.59%.
+  If 4bit feels lossy, 5bit is the tier to move to, not 6bit.
 - At the 4-bit tier this affine group-64 quant loses about half the perplexity MXFP4 does,
   costing 4.5 vs 4.25 bits/weight (~6% more storage, ~4% slower decode).
 All tiers are quantizations of the same weights, so this isolates the quantization scheme.
 Reproduce with [`bench.py`](https://github.com/PipeNetwork/defiant-fable-mlx).
+## Sampling## Sampling
 DavidAU's notes for this model, which carry over: