Instructions to use jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct 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("jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct")

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 jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct 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 "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"

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 jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct"

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 "jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct" \
  --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"

Qwen3.8-27B UD-Q3_K_XL — MLX imatrix-direct (native MLX, dynamic quant)

Native-MLX port of unsloth's UD-Q3_K_XL dynamic quantization for Qwen/Qwen3.8-27B. Runs the quantizer search natively in MLX's affine format (group size 64) and writes final MLX weights directly — no GGUF round-trip, no mlx_lm.convert re-quantization.

Perplexity (wikitext-2-raw first 32k tokens, 512-token windows):

Build	PPL ↓
unsloth UD-Q3_K_XL GGUF in llama.cpp	8.136
this model	8.136

The GPTQ variant of this build (jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-gptq-direct) improves this to 8.090 and is the recommended Q3 download.

Method

Bit map from unsloth's Qwen3.8-27B-UD-Q3_K_XL.gguf (dynamic per-tensor bit allocation).
Importance-weighted affine search per group using unsloth's published imatrix (per-column activation energies).
Final MLX weights emitted directly (packed uint32 codes + bf16 scales/biases) — the emitted weights are exactly what the search chose.

Limitations

Affine vs IQ-codebook gap. MLX quantized matmul supports only uniform affine grids; unsloth's ≤3-bit GGUFs use non-linear IQ codebooks. The gap vs GGUF is inherent to MLX's current kernels, not the weights.
Text-only. The base checkpoint's visual tower is not included.
Eval scope: wikitext-2, 32k tokens only; downstream tasks uncharacterized.
Not for further training.

Calibration data

Importance weighting: unsloth's published imatrix_unsloth.gguf.

Credits

unsloth — dynamic bit maps + imatrix
mlx-lm — MLX runtime
Pipeline: jclyons52/ud2mlx

Built 2026-08-28. Base model license inherited from Qwen/Qwen3.8-27B.

Downloads last month: 510

MLX

Hardware compatibility

Quantized

Model tree for jclyons52/Qwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-direct

Base model

Qwen/Qwen3.8-27B

Finetuned

(257)

this model