Instructions to use luxopes/Cognix-1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luxopes/Cognix-1-Flash with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="luxopes/Cognix-1-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luxopes/Cognix-1-Flash")
model = AutoModelForCausalLM.from_pretrained("luxopes/Cognix-1-Flash", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use luxopes/Cognix-1-Flash 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 luxopes/Cognix-1-Flash:F16
# Run inference directly in the terminal:
llama cli -hf luxopes/Cognix-1-Flash:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf luxopes/Cognix-1-Flash:F16
# Run inference directly in the terminal:
llama cli -hf luxopes/Cognix-1-Flash:F16

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 luxopes/Cognix-1-Flash:F16
# Run inference directly in the terminal:
./llama-cli -hf luxopes/Cognix-1-Flash:F16

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 luxopes/Cognix-1-Flash:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf luxopes/Cognix-1-Flash:F16

Use Docker

docker model run hf.co/luxopes/Cognix-1-Flash:F16

LM Studio
Jan

vLLM

How to use luxopes/Cognix-1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luxopes/Cognix-1-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luxopes/Cognix-1-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/luxopes/Cognix-1-Flash:F16

SGLang

How to use luxopes/Cognix-1-Flash with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "luxopes/Cognix-1-Flash" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luxopes/Cognix-1-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "luxopes/Cognix-1-Flash" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luxopes/Cognix-1-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use luxopes/Cognix-1-Flash with Ollama:
```
ollama run hf.co/luxopes/Cognix-1-Flash:F16
```
Unsloth Desktop

How to use luxopes/Cognix-1-Flash with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luxopes/Cognix-1-Flash:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "luxopes/Cognix-1-Flash:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use luxopes/Cognix-1-Flash with Docker Model Runner:
```
docker model run hf.co/luxopes/Cognix-1-Flash:F16
```

Lemonade

How to use luxopes/Cognix-1-Flash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull luxopes/Cognix-1-Flash:F16

Run and chat with the model

lemonade run user.Cognix-1-Flash-F16

List all available models

lemonade list

Hermes Agent

How to use luxopes/Cognix-1-Flash with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luxopes/Cognix-1-Flash:F16

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 luxopes/Cognix-1-Flash:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use luxopes/Cognix-1-Flash with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf luxopes/Cognix-1-Flash:F16

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 "luxopes/Cognix-1-Flash:F16" \
  --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"

Cognix 1 Flash

Created by LuxAI. This is the two-stage merged BF16 model. The original LFM2.5-1.2B Base was trained for one code-first SFT epoch: 324,074,287 input / 175,032,635 assistant-loss tokens. Original merged SFT is recoverable at luxopes/Cognix-1-Flash@4e01880fbfdfa5e20a8aff01266498fcf6b4d959; original SFT adapter at luxopes/Cognix-1-Flash-LoRA@ebe76821d0631681505d0044272c311ae775549e.

Final stage: rank16/alpha32, BF16 unquantized frozen base, learning rate2e-5, two planned epochs of 462 reviewed identity/physical-weapon-refusal/benign-adjacent/ helpful-cyber examples plus deterministic original code replay. Held-out47 examples were NOT trained. Actual final-stage updates: 153; input tokens: 679010; assistant-loss tokens: 409120. Completion: epochs.

IMPORTANT: the new adapter applies ONLY to the original merged SFT revision luxopes/Cognix-1-Flash@4e01880fbfdfa5e20a8aff01266498fcf6b4d959, not to LiquidAI base and NOT to the current already-merged two-stage model. Load that base with explicit revision="4e01880fbfdfa5e20a8aff01266498fcf6b4d959", then load this adapter with PEFT. Do not merge either adapter twice. The full BF16 model already contains both training stages and needs no adapters.

The unchanged native tokenizer/template and special tokens are included. Training used independent padded batch rows, assistant-only loss, no quantization, no new tokens, and a32768 context cap. Final supplement/replay rows are short; this is not evidence of tested long-context performance. No benchmarks or inference evaluations were run, and no quality or safety guarantees are claimed.

Original upstream LFM Open License v1.0 and source attributions remain applicable. See LICENSE, BASE_MODEL_CARD.md, DATA_ATTRIBUTION.md, POST_TRAINING_ATTRIBUTION.md, MAIN_TRAINING.json, POST_TRAINING_DATA.json and cognix_training.json for provenance. Public model release authorized by LuxAI on 2026-09-07. Additional GGUF downloads and evaluation reports are published with separate provenance; original training revisions remain available.

GGUF downloads

Both files contain the fully merged, two-stage Flash model; no adapter is required.

File	Format	Size
Cognix-1-Flash-F16.gguf	F16 (16-bit float)	2.343 GB
Cognix-1-Flash-Q8_0.gguf	Q8_0 (8-bit blocks)	1.246 GB

Converted locally with pinned llama.cpp; exact source revision and checksums are in GGUF_MANIFEST.json. Native vocabulary, special IDs and chat template are preserved. F16 is a BF16-to-FP16 export; Q8_0 is quantized from that F16 export, not QLoRA training. Some small tensors remain F32 as required by the standard GGUF implementation. Use a current llama.cpp-compatible runtime supporting LFM2. Select context explicitly, for example8192 initially and no more than32768 for the fine-tuning context range. The inherited128000 header comes from the upstream architecture config and does not constitute validation of a128k context or a memory-fit promise for8GB phones.

Measured limitations — 2026-09-07

This is an experimental model, not a reliable reasoning assistant. The final BF16 model was tested once on all 240 Czech Lux Core 1 tasks, with the native chat template, temperature 0, seed 42, 8192 context, 1024 output tokens (2048 for code). Code was executed in rootless Podman with no network, a read-only filesystem, 256 MiB memory, one CPU, 64 processes and no extra capabilities. All tasks completed; there were no API or sandbox errors and no skipped tasks.

Category	Correct	Accuracy
Math	9/40	22.50%
Code	19/40	47.50%
Knowledge	10/40	25.00%
Reasoning	2/40	5.00%
Reading	8/40	20.00%
Instructions	4/40	10.00%
Overall Lux score	52/240	21.67%

The score includes strict-format failures; it was not retrospectively relaxed. There are also substantive arithmetic and logic mistakes. Thirteen responses hit the output-token cap. Twelve additional qualitative probes found frequent invalid explanations: the age-equation example was correct, while a modular-arithmetic response contradicted its own correct final answer. Long explanations are not evidence of reliable reasoning.

Known identity issue: without an identity-setting system prompt, the final model falsely claimed OpenAI authorship in both English and Czech. The same English answer appeared in BF16, F16 GGUF and Q8_0 GGUF; this is not a GGUF-only observation. The intended identity is Cognix 1 Flash, fine-tuned by LuxAI on LiquidAI's base. No claim is made that identity or safety behavior is reliably learned.

F16 and Q8_0 were separately loaded and generated text with pinned llama.cpp b10826 on a local CPU. The Lux score is for BF16, not a GGUF benchmark. No phone-speed, 32k-context or base-model comparison was performed. See EVALUATION_SUMMARY.json for protocol and limitations.

Downloads last month: 26

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for luxopes/Cognix-1-Flash

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

(58)

this model

Adapters

2 models