Instructions to use sjakek/LFM-2.5-8B-1B-hermes-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir LFM-2.5-8B-1B-hermes-ft sjakek/LFM-2.5-8B-1B-hermes-ft

HERMES

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sjakek/LFM-2.5-8B-1B-hermes-ft",
	filename="gguf/LFM-2.5-8B-1B-Hermes-Tuned-Q4KXL.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sjakek/LFM-2.5-8B-1B-hermes-ft
# Run inference directly in the terminal:
llama-cli -hf sjakek/LFM-2.5-8B-1B-hermes-ft

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sjakek/LFM-2.5-8B-1B-hermes-ft
# Run inference directly in the terminal:
llama-cli -hf sjakek/LFM-2.5-8B-1B-hermes-ft

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf sjakek/LFM-2.5-8B-1B-hermes-ft
# Run inference directly in the terminal:
./llama-cli -hf sjakek/LFM-2.5-8B-1B-hermes-ft

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf sjakek/LFM-2.5-8B-1B-hermes-ft
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sjakek/LFM-2.5-8B-1B-hermes-ft

Use Docker

docker model run hf.co/sjakek/LFM-2.5-8B-1B-hermes-ft

LM Studio
Jan
Ollama
How to use sjakek/LFM-2.5-8B-1B-hermes-ft with Ollama:
```
ollama run hf.co/sjakek/LFM-2.5-8B-1B-hermes-ft
```

Unsloth Studio

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sjakek/LFM-2.5-8B-1B-hermes-ft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sjakek/LFM-2.5-8B-1B-hermes-ft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sjakek/LFM-2.5-8B-1B-hermes-ft to start chatting

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sjakek/LFM-2.5-8B-1B-hermes-ft"

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": "sjakek/LFM-2.5-8B-1B-hermes-ft"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sjakek/LFM-2.5-8B-1B-hermes-ft 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 "sjakek/LFM-2.5-8B-1B-hermes-ft"

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 sjakek/LFM-2.5-8B-1B-hermes-ft

Run Hermes

hermes

Docker Model Runner
How to use sjakek/LFM-2.5-8B-1B-hermes-ft with Docker Model Runner:
```
docker model run hf.co/sjakek/LFM-2.5-8B-1B-hermes-ft
```

Lemonade

How to use sjakek/LFM-2.5-8B-1B-hermes-ft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sjakek/LFM-2.5-8B-1B-hermes-ft

Run and chat with the model

lemonade run user.LFM-2.5-8B-1B-hermes-ft-{{QUANT_TAG}}

List all available models

lemonade list

LFM-2.5-8B-1B Hermes FT

This repo contains Hermes/tool-use fine-tuned variants of LiquidAI/LFM2.5-8B-A1B.

The current release candidate is iter13_llamacpp_chat_fixed. Earlier GGUF artifacts were withdrawn because they overfit tool routing and regressed normal chat by stopping too early. The iter13 repair adds a narrow chat-retention LoRA pass on top of the fixed Hermes tool-router model, then regenerates MLX and GGUF quants from the repaired fused checkpoint.

Runtime requirements

MLX releases preserve tool_parser_type: "pythonic".
llama.cpp GGUF releases are intended to be served with the LFM chat template, --jinja, and a 64K context smoke target.
Tested live server alias: sjakek/LFM-2.5-8B-1B-hermes-ft:Q6KXL.

Available artifacts

gguf/LFM-2.5-8B-1B-Hermes-Tuned-Q8KXL.gguf
gguf/LFM-2.5-8B-1B-Hermes-Tuned-Q6KXL.gguf
gguf/LFM-2.5-8B-1B-Hermes-Tuned-Q5KXL.gguf
gguf/LFM-2.5-8B-1B-Hermes-Tuned-Q4KXL.gguf
mlx/8bit/
mlx/6bit/
adapters/iter13_llamacpp_chat_retention_r8/
evals/iter13_*

Validation summary

All listed iter13 variants passed:

Normal-chat regression: 10/10
Fixed-Hermes tool-router suite: 43/43
Structured tool-call cases: 28/28
No-tool false positives: 0/10
Text tool-call leaks: 0

The normal-chat eval includes plain chat, tools-available no-tool chat, short factual answers, and multi-sentence explanations. The tool suite uses the fixed Hermes browser, terminal, file/search/write, no-tool, and tool-result finalization cases.

Training summary

Semi-full-gradient grouped MoE expert training over the Hermes trace corpus.
Fixed-Hermes contrastive router LoRA repairs for structured pythonic tool calls.
iter12 chat-retention repair to fix MLX normal-chat early stopping.
iter13 llama.cpp-targeted chat-retention repair after BF16 GGUF exposed shorter completions than MLX.

The GGUFs were regenerated from a dequantized fused safetensors source, then quantized from the BF16 GGUF parent. They are named Q*KXL as Hermes-tuned mixed-precision KXL targets.

Downloads last month: 1,564

Safetensors

Model size

8B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sjakek/LFM-2.5-8B-1B-hermes-ft

Base model

LiquidAI/LFM2.5-8B-A1B-Base

Finetuned

LiquidAI/LFM2.5-8B-A1B

Quantized

(44)

this model