Instructions to use dzdave/gpt-oss-20b-commit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dzdave/gpt-oss-20b-commit-mlx 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("dzdave/gpt-oss-20b-commit-mlx")

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 dzdave/gpt-oss-20b-commit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dzdave/gpt-oss-20b-commit-mlx"

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": "dzdave/gpt-oss-20b-commit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use dzdave/gpt-oss-20b-commit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "dzdave/gpt-oss-20b-commit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "dzdave/gpt-oss-20b-commit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "dzdave/gpt-oss-20b-commit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use dzdave/gpt-oss-20b-commit-mlx 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 "dzdave/gpt-oss-20b-commit-mlx"

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 dzdave/gpt-oss-20b-commit-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dzdave/gpt-oss-20b-commit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dzdave/gpt-oss-20b-commit-mlx"

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 "dzdave/gpt-oss-20b-commit-mlx" \
  --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"

gpt-oss-20b-commit-mlx / README.md

dzdave

Add gpt-oss-20b-commit fine-tune (MXFP4 MLX) + model card

e6abf74 verified 10 days ago

preview code

Raw

History Blame Contribute Delete

2.83 kB

metadata

license: apache-2.0
language:
  - en
base_model:
  - openai/gpt-oss-20b
tags:
  - mlx
  - gpt_oss
  - mxfp4
  - fine-tune
  - commit-message
  - code
library_name: mlx
pipeline_tag: text-generation

gpt-oss-20b-commit (MLX, MXFP4)

A LoRA fine-tune of openai/gpt-oss-20b specialised for git commit-message generation and closed-form, fully-anchored mechanical text edits. The adapter was fused into the base and the result quantised to MLX MXFP4 (attention and router kept at 8-bit affine). ~11 GB on disk, ~12 GB resident.

This is a genuine weight-level fine-tune, not a prompt wrapper. It is the Tier-3 "exactly this" executor in a local trading-agent stack — handed a file, a verbatim anchor, and the exact text to produce, and nothing wider.

What it is good at (measured)

Scored on a fixed grader written before the model ran, one model resident at a time, temperature 0.2.

Task	Result
Anchored mechanical edit (5 edits, byte-identity)	10/10 — byte-identical to the reference
Generate two modules from a spec	8/8
Concurrency + backpressure implementation	7/10
First-attempt Pydantic-schema validity	8/8

The anchored-edit 10/10 is the job it exists for: given file + exact anchor + exact replacement, it reproduces the reference edit exactly.

What it must NOT be used for

This tune traded agentic capability for its edit precision. Do not put it on a tool-calling or numeric path. Measured regressions vs. the base:

Tool-deference 0/5 — it computes numbers in its head and invents them (e.g. a stop of 235.20 from 250 − 2×7.40) instead of calling a tool. Never let it emit a number to a human.
Multi-tool selection 2/8 — frequently answers in prose instead of calling any tool.
Multi-turn policy/steps 2/4 · 1/4 — unreliable as an orchestrator.

Keep it for mechanical text transforms and commit messages; route judgement, tool use, and anything that emits a number elsewhere.

Runtime footguns

It repeats its output — truncate to the first occurrence.
It hangs on a stop parameter — bound generation with max_tokens instead.

Use it

pip install mlx-lm
python -m mlx_lm generate --model dzdave/gpt-oss-20b-commit-mlx \
  --prompt "Write a git commit message for: <diff>" --max-tokens 256

Also loads directly in LM Studio (MLX runtime).

Provenance & license

Base: openai/gpt-oss-20b (Apache-2.0), fused onto the mlx-community/gpt-oss-20b-MXFP4-Q8 MLX build.
Method: LoRA fine-tune on commit-message data, adapters fused, then MXFP4 quantisation.
License: Apache-2.0, inherited from the base. Attribution to OpenAI's gpt-oss-20b required.
Architecture GptOssForCausalLM · gpt_oss · MoE 32×2.4B.