Instructions to use tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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("tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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
LM Studio

Pi new

How to use tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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 "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx"

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": "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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 "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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 tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx

Run Hermes

hermes

MLX LM

How to use tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-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 "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

GPT-OSS-Swallow-120B-RL-v0.1 — MLX 6-bit

6-bit quantized MLX version of tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1, optimized for Apple Silicon.

Key Details

Architecture: gpt_oss (Mixture of Experts — 117B total, 5.1B active)
Quantization: 6-bit (6.504 bits/weight)
Disk size: ~89 GB
Peak memory: ~95 GB
Generation speed: ~74 tok/s on M4 Max 128GB
Requires: 128GB unified memory (Apple Silicon)

Usage

pip install mlx-lm

mlx_lm.generate \
  --model tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx \
  --prompt "日本の首都はどこですか？" \
  --max-tokens 200

from mlx_lm import load, generate

model, tokenizer = load("tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx")

messages = [{"role": "user", "content": "Pythonでフィボナッチ数列を出力するコードを書いてください"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)

response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=500)

License

Apache 2.0 (inherited from base model)

Downloads last month: 309

Safetensors

Model size

26B params

Tensor type

BF16

U32

MLX

Hardware compatibility

6-bit

Model tree for tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx

Base model

tokyotech-llm/GPT-OSS-Swallow-120B-SFT-v0.1

Finetuned

tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1

Quantized

(7)

this model