Instructions to use juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juanquivilla/sotto-cleanup-lfm25-350m-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("juanquivilla/sotto-cleanup-lfm25-350m-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
LM Studio

Pi new

How to use juanquivilla/sotto-cleanup-lfm25-350m-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 "juanquivilla/sotto-cleanup-lfm25-350m-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": "juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use juanquivilla/sotto-cleanup-lfm25-350m-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 "juanquivilla/sotto-cleanup-lfm25-350m-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 juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit

Run Hermes

hermes

MLX LM

How to use juanquivilla/sotto-cleanup-lfm25-350m-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 "juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "juanquivilla/sotto-cleanup-lfm25-350m-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": "juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

SottoASR Transcript Cleanup — LFM2.5-350M MLX 4-bit (soup_30)

sottoasr.app · Full precision (bf16) · MLX 5-bit (recommended)

Overview

MLX 4-bit affine quantization of juanquivilla/sotto-cleanup-lfm25-350m. Smallest variant. The 5-bit MLX variant is recommended for most users.

What's new in soup_30

soup_30 extends v45 with targeted training data for five failure modes (multi-number sentences, year-context drift, disconnected number lists, within-input duplicates, long-form preservation), each generated programmatically and audited with a Qwen3.6-27B judge.

Metric	v45	soup_30
Number accuracy	95.9%	96.5%
Adversarial benchmark (greedy)	76%	86%

See the bf16 model card for the full pipeline and benchmark numbers.

Quantization Recipe

mlx_lm.convert \
  --hf-path juanquivilla/sotto-cleanup-lfm25-350m \
  --mlx-path sotto-cleanup-lfm25-350m-mlx-4bit \
  -q --q-bits 4 --q-group-size 64 \
  --trust-remote-code

Usage

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load("juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit")
sampler = make_sampler(temp=0.0)

text = "talk about server three sixty"
prompt = f"### Input:\n{text}\n\n### Output:\n"
output = generate(model, tokenizer, prompt=prompt, max_tokens=512, sampler=sampler)
if "###" in output:
    output = output[:output.index("###")].strip()
print(output)

License

MIT

Downloads last month: 105

Safetensors

Model size

55.4M params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for juanquivilla/sotto-cleanup-lfm25-350m-mlx-4bit

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

juanquivilla/sotto-cleanup-lfm25-350m

Quantized

(2)

this model