Instructions to use vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit 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("vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit")
config = load_config("vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit")

# 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 vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit"

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": "vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit"

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 "vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit" \
  --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"

Hermes Agent

How to use vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit 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 "vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit"

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 vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-8bit

Run Hermes

hermes

Atomic Chat

vanch007 commited on Mar 18

Commit

ab3e909

verified ·

1 Parent(s): 87c570d

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +115 -110

config.json CHANGED Viewed

@@ -1,113 +1,118 @@
 {
-    "architectures": [
-        "Qwen3_5ForConditionalGeneration"
     ],
-    "image_token_id": 248056,
-    "model_type": "qwen3_5",
-    "quantization": {
-        "group_size": 64,
-        "bits": 8,
-        "mode": "affine"
-    },
-    "quantization_config": {
-        "group_size": 64,
-        "bits": 8,
-        "mode": "affine"
-    },
-    "text_config": {
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "attn_output_gate": true,
-        "dtype": "bfloat16",
-        "eos_token_id": 248044,
-        "full_attention_interval": 4,
-        "head_dim": 256,
-        "hidden_act": "silu",
-        "hidden_size": 4096,
-        "initializer_range": 0.02,
-        "intermediate_size": 12288,
-        "layer_types": [
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention",
-            "linear_attention",
-            "linear_attention",
-            "linear_attention",
-            "full_attention"
-        ],
-        "linear_conv_kernel_dim": 4,
-        "linear_key_head_dim": 128,
-        "linear_num_key_heads": 16,
-        "linear_num_value_heads": 32,
-        "linear_value_head_dim": 128,
-        "max_position_embeddings": 262144,
-        "mlp_only_layers": [],
-        "model_type": "qwen3_5_text",
-        "mtp_num_hidden_layers": 1,
-        "mtp_use_dedicated_embeddings": false,
-        "num_attention_heads": 16,
-        "num_hidden_layers": 32,
-        "num_key_value_heads": 4,
-        "rms_norm_eps": 1e-06,
-        "use_cache": true,
-        "vocab_size": 248320,
-        "mamba_ssm_dtype": "float32",
-        "rope_parameters": {
-            "mrope_interleaved": true,
-            "mrope_section": [
-                11,
-                11,
-                10
-            ],
-            "rope_type": "default",
-            "rope_theta": 10000000,
-            "partial_rotary_factor": 0.25
-        }
     },
-    "tie_word_embeddings": false,
-    "transformers_version": "4.57.0.dev0",
-    "video_token_id": 248057,
-    "vision_config": {
-        "deepstack_visual_indexes": [],
-        "depth": 27,
-        "hidden_act": "gelu_pytorch_tanh",
-        "hidden_size": 1152,
-        "in_channels": 3,
-        "initializer_range": 0.02,
-        "intermediate_size": 4304,
-        "model_type": "qwen3_5",
-        "num_heads": 16,
-        "num_position_embeddings": 2304,
-        "out_hidden_size": 4096,
-        "patch_size": 16,
-        "spatial_merge_size": 2,
-        "temporal_patch_size": 2
-    },
-    "vision_end_token_id": 248054,
-    "vision_start_token_id": 248053
-}

 {
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "quantization": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "dtype": "bfloat16",
+    "eos_token_id": 248046,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
     ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "vocab_size": 248320,
+    "mamba_ssm_dtype": "float32",
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "rope_type": "default",
+      "rope_theta": 10000000,
+      "partial_rotary_factor": 0.25
     },
+    "bos_token_id": 248045,
+    "pad_token_id": 248044
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "bos_token_id": 248045,
+  "eos_token_id": 248046,
+  "pad_token_id": 248044
+}