Instructions to use rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 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("rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32")

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 rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"

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": "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 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 "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"

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 rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32

Run Hermes

hermes

OpenClaw new

How to use rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"

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 "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32" \
  --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 rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "rubybear/FastContext-1.0-4B-SFT-mlx-4bit-g32",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

FastContext-1.0-4B-SFT-mlx-4bit-g32 / README.md

rubybear

Upload 4-bit g32 quantization of FastContext-1.0-4B-SFT

25a0466 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.42 kB

	---
	language:
	- en
	license: mit
	tags:
	- Explorer SubAgent
	- Repository Exploration
	- mlx
	library_name: mlx
	base_model: microsoft/FastContext-1.0-4B-SFT
	pipeline_tag: text-generation
	---

	# FastContext-1.0-4B-SFT-mlx-4bit-g32

	4-bit MLX quantization of [microsoft/FastContext-1.0-4B-SFT](https://huggingface.co/microsoft/FastContext-1.0-4B-SFT) with group_size=32 for Apple Silicon.

	## Quantization details

	- Method: Affine 4-bit
	- Group size: 32 (finer than the default 64)
	- Effective bits per weight: 5.0
	- Model size: 2.4 GB (vs 7.5 GB bf16)

	## Benchmark results

	Tested on 10 SWE-bench Multilingual instances against other quantization variants:

	\| Model \| Bits/Wt \| Size \| File F1 \| Line F1 \|
	\|-------\|---------\|------\|---------\|---------\|
	\| affine 8-bit g64 \| 8.5 \| 4.0G \| 0.507 \| 0.140 \|
	\| affine 4-bit g32 (this model) \| 5.0 \| 2.4G \| 0.300 \| 0.090 \|
	\| affine 3-bit g64 \| 3.5 \| 1.7G \| 0.100 \| 0.000 \|
	\| affine 4-bit g64 \| 4.5 \| 2.1G \| 0.050 \| 0.005 \|
	\| mattrobenolt 4-bit g64 \| 4.5 \| 2.1G \| 0.025 \| 0.008 \|

	The finer group_size=32 delivers 12x better File F1 than standard 4-bit g64 quantization with only 300MB additional size.

	## Usage

	```python
	from mlx_lm import load, generate

	model, tokenizer = load("rubybear-lgtm/FastContext-1.0-4B-SFT-mlx-4bit-g32")
	```

	Or with [fastcontext-mcp](https://github.com/rubybear-lgtm/fastcontext) for Claude Code integration.