Instructions to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"

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": "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"

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 "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit" \
  --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"

MLX LM

How to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit 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 "AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit"

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 AutomatosX/AX-gpt-oss-20b-MLX-AXQ-6bit

Run Hermes

hermes

Atomic Chat

AX-gpt-oss-20b-MLX-AXQ-6bit / axquant_quantizer_execution.json

AutomatosX

Rebuild from openai/gpt-oss-20b native MXFP4 mixed source (AXQ-6bit architecture_prior 6.0); replace mlx-community Q4 re-pack lineage.

66d0ce8 verified 4 days ago

Raw

History Blame Contribute Delete

42 kB

	{
	"created_at": "2026-08-12T01:08:12.637062Z",
	"plan_sha256": "77daba154be0d240dc23c32b3ffd19e5c4c24ddb1d6139f9ed7ef29d4d78ebbf",
	"records": [
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.0.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.1.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.10.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.11.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.12.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.13.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.14.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.15.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.16.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.17.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.18.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.19.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.2.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.20.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 4,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.21.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.22.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.23.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.3.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.4.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.5.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.embed_tokens",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.6.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.7.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.8.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.mlp.experts.down_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.mlp.experts.gate_up_proj_blocks",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.mlp.router",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.self_attn.k_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.self_attn.o_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 6,
	"fallback": false,
	"group_size": 32,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.self_attn.q_proj",
	"note": "mlx-lm affine packing",
	"success": true
	},
	{
	"bits": 8,
	"fallback": false,
	"group_size": 64,
	"metadata": {},
	"method": "affine",
	"module_path": "model.layers.9.self_attn.v_proj",
	"note": "mlx-lm affine packing",
	"success": true
	}
	],
	"schema_version": "axquant.quantizer-execution.v1"
	}