Instructions to use netprojects/GLiDE-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netprojects/GLiDE-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("netprojects/GLiDE-mlx-8bit")
config = load_config("netprojects/GLiDE-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 netprojects/GLiDE-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 "netprojects/GLiDE-mlx-8bit"

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": "netprojects/GLiDE-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use netprojects/GLiDE-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 "netprojects/GLiDE-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 netprojects/GLiDE-mlx-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use netprojects/GLiDE-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 "netprojects/GLiDE-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 "netprojects/GLiDE-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"

GLiDE — MLX 8-bit

Built and tested on Apple M5 Max (128 GB) · upstream revision GLiDE v1.2 (d199b6d)

An 8-bit MLX conversion (affine, group size 64) of fastino/GLiDE (GLiDE v1.2, revision d199b6d), Fastino's decision model built on Qwen3.8-27B, for Apple Silicon. 28.2 GB of weights.

Built with Fastino GLiDE. Published by NetProjects (Internet Projects Ltd). Not affiliated with Fastino.

GLiDE is a decision model, not a chat model. Give it a state (text, JSON or images) and typed questions (choice, noul for yes / no, score) and it returns a probability for every option, in one forward pass per question. Nothing is generated.

Serve it with glide-mlx, not with mlx_lm.server or a plain mlx_vlm generate call. GLiDE reads its answer from a separate 255-way readout (readout.safetensors) and lets its full-attention layers read the whole prompt in both directions; generic MLX snippets do neither.

Results (MacBook Pro M5 Max, 128 GB, 29 October 2026)

	this checkpoint
Same top answer as Fastino's own PyTorch code (bf16)	202 / 204 questions; probability difference mean 0.002
Same top answer as the original weights on MLX (bf16)	204 / 204
JevBench public (231, JevBench v1.2.1, `--adapter typesafe`)	215 / 231 (easy 48/48 · standard 72/72 · hard 95/111)
Time per JevBench item (prompts up to about 4K tokens)	0.74 s median

The two answers that differ from Fastino's code are near-ties in the reference itself (top-two margin 0.018 and 0.000). The comparison set has 72 requests with 204 questions: text and JSON states of 30 to 1,500 words, 12 image requests, and all three question types. Practically identical to the original weights; the recommended MLX build.

What is kept as in the original

Reading: the 16 full-attention layers see the whole prompt (no causal mask), the 48 Gated DeltaNet layers keep their recurrence, as GLiDE's noncausal_full_attention.
Answer: the last token's hidden state goes through GLiDE's 255-way readout, kept at its original precision; softmax over the options at the temperature in decision_config.json.
Prompts and images: GLiDE's own prompt.py and images.py, unchanged; the vision encoder stays at its original precision.
API: the same POST /v1/systemone request and response format as GLiDE's server.

Use

git clone https://github.com/internet-projects/glide-mlx && cd glide-mlx
uv venv --python 3.12 .venv && uv pip install --python .venv/bin/python -r requirements.txt
hf download netprojects/GLiDE-mlx-8bit --local-dir glide-mlx-8bit
.venv/bin/python -m glide_mlx.server --model glide-mlx-8bit --port 8790    # http://127.0.0.1:8790/v1/systemone

curl -s localhost:8790/v1/systemone -H 'Content-Type: application/json' -d '{
  "state": "Order 123 arrived broken and the customer wants their money back.",
  "questions": {"intent": {"type": "choice", "instructions": "What does the customer want?",
                           "criteria": {"refund": "A refund", "exchange": "An exchange", "info": "Information"}},
                "angry": {"type": "noul", "instructions": "Is the customer angry?"}}}'

Python: from glide_mlx import GlideMLX; g = GlideMLX.from_pretrained("glide-mlx-8bit"); g.decide(state, questions).

Smaller: netprojects/GLiDE-mlx-4bit (15.3 GB). Full precision: the original fastino/GLiDE folder loads directly with the same code.

License

GLiDE is licensed under the Fastino Community License (LICENSE, NOTICE, licenses/Qwen3.8-27B-LICENSE are included). This conversion is a Derivative Work under that license and is distributed under the same terms. In short: commercial use requires displaying "Built with Fastino GLiDE" (section 4), and production commercial use by an entity with annual revenue above USD 10 million requires a separate agreement with Fastino (sections 2–3). Read the license for the full terms.

Credits: Fastino (GLiDE), Qwen team (Qwen3.8-27B, Apache-2.0), MLX and mlx-vlm. Conversion by Paris Michalas, Partner at NetProjects. Not affiliated with Fastino.

More NetProjects MLX builds: NetProjects MLX builds collection · all models at huggingface.co/netprojects