Instructions to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

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 NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

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 NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with Ollama:
```
ollama run hf.co/NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
```

Unsloth Studio

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF 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 NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF 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 NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF to start chatting

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M
```

Lemonade

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Saiga-It-v3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

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 NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M

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 "NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

LFM2.5-1.2B-Saiga-It-v3

Continued attempt to make a Russian-language Saiga out of LFM2.5 1.2B by Liquid AI. This is v3 — a significant upgrade over v2 with much more CPT data.

Inspired by the amazing work of Ilya Gusev and the Saiga project.

What changed vs v2?

CPT dataset grew from ~1.25M to ~2.69M examples:

Full Russian Wikipedia (~1.9M articles, up from 350k)
Added Habr (~295k technical articles in Russian)
Replaced c4 ru with CulturaX ru (200k)
Kept English c4 (300k) for retention

SFT dataset expanded:

Added IlyaGusev/ru_turbo_saiga
Added lksy/ru_instruct_gpt4

Training

Stage 1 — Continued Pre-Training (CPT):

wikimedia/wikipedia (Russian, ~1.9M articles)
IlyaGusev/habr (Russian, ~295k technical articles)
uonlp/CulturaX (Russian, 200k)
allenai/c4 (English, 300k for retention)
10,000 steps, lr=3e-5, loss 2.26 → 2.13

Stage 2 — Supervised Fine-Tuning (SFT):

IlyaGusev/saiga_scored (opus_score ≥ 8, ~27k)
d0rj/alpaca-cleaned-ru (15k)
IlyaGusev/ru_sharegpt_cleaned
IlyaGusev/ru_turbo_saiga
lksy/ru_instruct_gpt4
2 epochs, lr=5e-6, final loss ~1.21

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "NickupAI/LFM2.5-1.2B-Saiga-It-v3",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "NickupAI/LFM2.5-1.2B-Saiga-It-v3",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Привет! Как дела?"}]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    temperature=0.1,
    top_k=50,
    top_p=0.1,
    repetition_penalty=1.05,
    do_sample=True,
)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Honest Warning ⚠️

Still hallucinates. Training a model of this size properly requires significantly more compute and time than was available for this project — the CPT data barely scratches the surface of what would be needed for reliable factual knowledge. The model knows the format of answers but sometimes invents the content.

Recommended for:

Creative nonsense generation, lol
Experiments and research
Russian language generation tasks

Not recommended for:

Factual questions
Medicine, law or any serious topics
Astronomy (the dwarf planet situation has not improved)

— Назови все карликовые планеты Солнечной системы

Марс, 2. Венус, 3. Земля, 4. Юпитер... 8. Эритрея

v2 had Kvass and Gamma-Tit. v3 replaced them with Eritrea. Progress.

GGUF versions

Quantized versions available at NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF.

What's next

LoRA experiments on larger base models (7B+). The 1.2B size has fundamental limitations for factual knowledge — time to scale up.

GGUF Versions

Quantized versions of the model.

Downloads last month: 159

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Finetuned

NickupAI/LFM2.5-1.2B-Saiga-It-v3

Quantized

(3)

this model

NickupAI
/

LFM2.5-1.2B-Saiga-It-v3-GGUF

LFM2.5-1.2B-Saiga-It-v3

What changed vs v2?

Training

Usage

Honest Warning ⚠️

GGUF versions

What's next

GGUF Versions

Model tree for NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF

Datasets used to train NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF