Instructions to use JANGQ-AI/LFM2.5-8B-A1B-JANG_2L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JANGQ-AI/LFM2.5-8B-A1B-JANG_2L 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("JANGQ-AI/LFM2.5-8B-A1B-JANG_2L")

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 JANGQ-AI/LFM2.5-8B-A1B-JANG_2L with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"

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": "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use JANGQ-AI/LFM2.5-8B-A1B-JANG_2L with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use JANGQ-AI/LFM2.5-8B-A1B-JANG_2L 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 "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"

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 JANGQ-AI/LFM2.5-8B-A1B-JANG_2L

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JANGQ-AI/LFM2.5-8B-A1B-JANG_2L with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L"

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 "JANGQ-AI/LFM2.5-8B-A1B-JANG_2L" \
  --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"

LFM2.5-8B-A1B-JANG_2L / README.md

jangq

Add vMLX app banner and runtime note to model card

5fb8277 verified 22 days ago

preview code

Raw History Blame

3.11 kB

metadata

language:
  - en
  - ar
  - zh
  - fr
  - de
  - ja
  - ko
  - es
  - pt
license: other
license_name: lfm1.0
license_link: LICENSE
base_model: LiquidAI/LFM2.5-8B-A1B
pipeline_tag: text-generation
library_name: mlx
tags:
  - mlx
  - jang
  - jang-2l
  - lfm2.5
  - liquid
  - text-generation

⚡ All JANG models are meant to be run in vMLX

LFM2.5-8B-A1B-JANG_2L

JANG_2L conversion of LiquidAI/LFM2.5-8B-A1B, built for Apple Silicon inference through JANG-aware MLX/vMLX runtimes.

This bundle is not a plain MLX 2-bit quant. It uses JANG importance allocation over MLX affine quantized tensors, with higher precision reserved for runtime-sensitive tensors.

Format

Format: JANG affine
Profile: JANG_2L
Quantization backend: mx.quantize
Group size: 64
Actual bits from jang_config.json: 2.37
Bit widths used: 2, 6, 8
Passthrough bit width: 16
Local size before upload: 2.9G
JANG runtime weight size metadata: 2.84 GB
Source model: LiquidAI/LFM2.5-8B-A1B

Runtime capability stamp:

{
  "reasoning_parser": "qwen3",
  "tool_parser": "lfm2",
  "think_in_template": false,
  "supports_tools": true,
  "supports_thinking": true,
  "family": "lfm2_moe",
  "modality": "text",
  "cache_type": "hybrid"
}

Runtime

Use a JANG-aware MLX/vMLX runtime. The model has hybrid cache behavior: attention layers use KV cache, while LIV convolution layers use convolution/state cache.

Example with the local JANG tools runtime:

python -m jang_tools inference \
  --model OsaurusAI/LFM2.5-8B-A1B-JANG_2L \
  --prompt "What is 2+2? Answer briefly." \
  --max-tokens 128 \
  --temperature 0

Chat Template And Reasoning

The bundled chat_template.jinja uses Liquid's ChatML-like format:

User and assistant turns use <|im_start|> / <|im_end|>.
The generation prompt ends at <|im_start|>assistant\n; it does not pre-open <think>.
Assistant reasoning may appear inside <think>...</think>.
Tool calls use Liquid's Python-call list format inside <|tool_call_start|> and <|tool_call_end|>.

For this bundle, think_in_template=false is intentional. Runtime code should parse reasoning if the model emits it, but should not force a second reasoning prefix.

Verification

Local smoke run on the converted bundle:

Prompt: What is 2+2? Answer briefly.
Result: output closed <think>...</think> and answered 2 + 2 = 4.
Reported generation speed: 206.886 tok/s
Load time: 1.946 s
Peak RSS: 3887 MB

This is a smoke test, not a benchmark suite or accuracy evaluation.

Korean

이 모델은 LiquidAI/LFM2.5-8B-A1B를 JANG_2L 형식으로 변환한 Apple Silicon용 번들입니다. think_in_template=false가 의도된 설정이며, 런타임은 모델이 생성한 <think>...</think>를 파싱하되 별도의 reasoning 접두어를 강제로 추가하지 않아야 합니다.