Instructions to use pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit 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("pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit")

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 pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"

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": "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit 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 "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"

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 pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit"

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 "pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit" \
  --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"

LFM2.5-24B-A2B for mlx-serve (mixed 4-bit / 8-bit)

An affine MLX quantization of LiquidAI/LFM2.5-24B-A2B. It carries the source repository's LFM 1.0 license unchanged.

This is a text-only model. Its native architecture is lfm2_moe (Lfm2MoeForCausalLM), which is supported natively by mlx-serve v26.10.2 and later; it is not a Qwen-engine conversion.

Benchmark results

Recorded comparison with LiquidAI/LFM2.5-24B-A2B-MLX-4bit:

Metric	Stock 4-bit	Mixed 4/8-bit	Delta
Plain decode	85.68 tok/s	189.75 tok/s	+121.5% (2.21×)
Plain prefill	409.71 tok/s	733.09 tok/s	+78.9%
Best decode	180.45 tok/s	184.95 tok/s	+2.5%
Best prefill	482.32 tok/s	460.79 tok/s	-4.5%

Long-context ladder

Rung	Stock prefill / decode	Mixed prefill / decode	Needle
4K	1222 tok/s / 128 tok/s	2644 tok/s / 143 tok/s	Passed / Passed
16K	1263 tok/s / 84 tok/s	2441 tok/s / 104 tok/s	Passed / Passed
32K	1082 tok/s / 67 tok/s	2156 tok/s / 79 tok/s	Passed / Passed
64K	866 tok/s / 31 tok/s	1674 tok/s / 52 tok/s	Passed / Passed
128K	—	—	Both packs failed at the 131,072-token ceiling.

Quantization

Routed MoE experts: affine 4-bit, group size 64.
Trunk projections (attention, convolution, and dense MLP layers): affine 8-bit, group size 64.
Token embeddings: affine 6-bit, group size 64.
Router gates and norms: BF16; expert-selection bias: float32.

Usage

Requires mlx-serve v26.10.2 or later.

mlx-serve serve --model pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit

Downloads last month: 258

Safetensors

Model size

25B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

4-bit

Model tree for pgmharikrishnan/LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit

Base model

LiquidAI/LFM2.5-24B-A2B-Base

Finetuned

LiquidAI/LFM2.5-24B-A2B

Quantized

(69)

this model