Instructions to use LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 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("LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4")
config = load_config("LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4")

# 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

Unsloth Studio

How to use LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4",
    max_seq_length=2048,
)

How to use LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4"

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": "LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 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 "LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4"

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 LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4

Run Hermes

hermes

mszymanska commited on May 12

Commit

e296167

verified ·

1 Parent(s): ef53aee

docs: add Validation section with pipeline test data (M3 Ultra, 2026-04-22)

Browse files

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -84,11 +84,24 @@ This card reports metadata present in the Hugging Face repository, existing fron
 Use the library instructions above, or run this checkpoint through the tested local serving path: [`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server)
 ## Limitations
-- No public benchmark results are declared in this card.
 - Validate outputs on your own domain data before relying on this checkpoint.
 - Memory use and speed depend heavily on Apple Silicon generation, unified-memory size, prompt length, and runtime configuration.
 ## License

 Use the library instructions above, or run this checkpoint through the tested local serving path: [`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server)
+## Validation
+End-to-end pipeline test 2026-04-22 on M3 Ultra (load → text → vision → unload), served via `mlx-batch-server`:
+| Probe | TTFT | Output chars | Notes |
+|---|---|---|---|
+| Cold load | — | — | **21 s** from cold to ready |
+| Text — simple greeting (PL) | 0.51 s | 601 | Clean output, abliterated behaviour |
+| Text — canonical (PL, literary) | 0.29 s | 718 | Concise reasoning trace |
+| Vision — JPEG (Monument Valley) | 6.50 s | 873 | Accurate scene description |
+3/3 probes passed. `has_reasoning=True` on all probes — this model emits reasoning traces via `<think>` markers.
 ## Limitations
 - Validate outputs on your own domain data before relying on this checkpoint.
 - Memory use and speed depend heavily on Apple Silicon generation, unified-memory size, prompt length, and runtime configuration.
+- Validation data above reflects M3 Ultra; expect different timings on other hardware.
 ## License