Instructions to use nightscape/Intern-S2-Mobius-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightscape/Intern-S2-Mobius-4bit-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("nightscape/Intern-S2-Mobius-4bit-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 nightscape/Intern-S2-Mobius-4bit-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 "nightscape/Intern-S2-Mobius-4bit-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": "nightscape/Intern-S2-Mobius-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nightscape/Intern-S2-Mobius-4bit-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 "nightscape/Intern-S2-Mobius-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightscape/Intern-S2-Mobius-4bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightscape/Intern-S2-Mobius-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use nightscape/Intern-S2-Mobius-4bit-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 "nightscape/Intern-S2-Mobius-4bit-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 nightscape/Intern-S2-Mobius-4bit-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nightscape/Intern-S2-Mobius-4bit-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 "nightscape/Intern-S2-Mobius-4bit-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 "nightscape/Intern-S2-Mobius-4bit-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"

Intern-S2-Mobius-4bit-mlx / README.md

nightscape

Add Intern-S2-Mobius 4-bit MLX (group-64) conversion

b23eaff verified 4 days ago

preview code

Raw

History Blame Contribute Delete

2.6 kB

	---
	library_name: mlx
	license: apache-2.0
	license_link: https://huggingface.co/internlm/Intern-S2-Mobius/blob/main/LICENSE
	pipeline_tag: text-generation
	base_model: internlm/Intern-S2-Mobius
	tags:
	- mlx
	- mlx-lm
	- quantization
	- 4-bit
	---

	# Intern-S2-Mobius (4-bit MLX)

	An MLX 4-bit (affine, group size 64) quantization of
	[internlm/Intern-S2-Mobius](https://huggingface.co/internlm/Intern-S2-Mobius) — a 35B hybrid model:
	Gated-DeltaNet linear attention / full attention at interval 4, with 2560 experts in 4 globally-shared
	routed MoE banks. Runs on Apple Silicon.

	- Base model: [internlm/Intern-S2-Mobius](https://huggingface.co/internlm/Intern-S2-Mobius) (Apache-2.0).
	- Quantization: 4-bit affine, group size 64; shared-expert / router gates kept at 8-bit. ~19.6 GB peak, ~4.5 bpw.
	- Architecture: `interns2_mobius` (`text_config.model_type = interns2_mobius_text`), 40 layers, `head_dim` 256,
	MoE 2560 experts / top-8, `num_blocks` 4. `max_position_embeddings` 262144.

	## Quick start

	Requires the `mlx-lm` build that ships the `interns2_mobius` architecture
	(official part of `mlx-lm` as of the model-support PR):

	```bash
	pip install -U mlx-lm
	mlx_lm.generate --model nightscape/Intern-S2-Mobius-4bit-mlx \
	-p "The secret to baking a good cake is" -m 1024 --trust-remote-code
	```

	`--trust-remote-code` is mandatory: the checkpoint bundles a custom tokenizer
	(`tokenization_interns1.py`) and model code.

	## Details

	- This is an MLX conversion; `transformers` does not yet ship `interns2_mobius`. The reference is the
	upstream repo's `trust_remote_code` implementation, verified by full bf16 logit diff (argmax agreement
	38/39, the sole miss a bit-identical tie).
	- Capability spot-check (this 4-bit conversion): MMLU-Pro 88.3% ± 4.1 (n=60) vs upstream bf16 89.05;
	GSM8K 97–98% (n=100). Short-generation-budget evals truncate chain-of-thought and depress scores — an
	eval artifact, not a capability drop.
	- Text-only: this conversion is the language model. The upstream checkpoint is tagged `image-text-to-text`,
	but the MLX port loads the language model and generates text (no vision tower on this path).

	## Companion

	An experimental MTP (Multi-Token-Prediction) head is published separately:
	[nightscape/Intern-S2-Mobius-4bit-mlx-mtp](https://huggingface.co/nightscape/Intern-S2-Mobius-4bit-mlx-mtp).
	It is consumed by the `omlx` server's `interns2_mobius` MTP driver, not by stock `mlx-lm`.

	## License

	Weights and code under Apache-2.0 — see [LICENSE](LICENSE). Model by InternLM; this is a derivative
	conversion of their weights plus the MLX port.