Instructions to use pipenetwork/FrogBoss-32B-2510-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/FrogBoss-32B-2510-MLX-4bit 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("pipenetwork/FrogBoss-32B-2510-MLX-4bit")

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 pipenetwork/FrogBoss-32B-2510-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/FrogBoss-32B-2510-MLX-4bit"

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": "pipenetwork/FrogBoss-32B-2510-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/FrogBoss-32B-2510-MLX-4bit 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 "pipenetwork/FrogBoss-32B-2510-MLX-4bit"

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 pipenetwork/FrogBoss-32B-2510-MLX-4bit

Run Hermes

hermes

MLX LM

How to use pipenetwork/FrogBoss-32B-2510-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/FrogBoss-32B-2510-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/FrogBoss-32B-2510-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/FrogBoss-32B-2510-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

FrogBoss-32B-2510-MLX-4bit

4-bit MLX quantization of microsoft/FrogBoss-32B-2510 — Microsoft's 32B debugging/software-engineering finetune of Qwen3-32B (SFT on debugging trajectories; ~45% pass@1 on SWE-bench Verified). Converted with mlx-lm for Apple Silicon.

Other quantizations: 4-bit (this) · 8-bit

📚 Part of the Frog (SWE/debugging) MLX collection.


Precision	MLX affine 4-bit, group 64
Size	17 GB
Base arch	Qwen3-32B (Qwen3) · 64K context
License	MIT

Usage

mlx_lm.server --model pipenetwork/FrogBoss-32B-2510-MLX-4bit --port 8080

from mlx_lm import load, generate
model, tok = load("pipenetwork/FrogBoss-32B-2510-MLX-4bit")

Conversion

mlx_lm.convert --hf-path microsoft/FrogBoss-32B-2510 --mlx-path <out> -q --q-bits 4 --q-group-size 64

Converted by pipenetwork. Original model & MIT license by Microsoft; not affiliated.

Downloads last month: 15

Safetensors

Model size

33B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for pipenetwork/FrogBoss-32B-2510-MLX-4bit

Base model

Qwen/Qwen3-32B

Finetuned

microsoft/FrogBoss-32B-2510

Quantized

(7)

this model

Collection including pipenetwork/FrogBoss-32B-2510-MLX-4bit

Frog (SWE/debugging) MLX

Collection

MLX quants of Microsoft's FrogBoss-32B & FrogMini-14B (Qwen3 debugging finetunes, SWE-bench ~45% pass@1) for Apple Silicon. • 4 items • Updated 3 days ago