Instructions to use onepass-st/caliber-flex-5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onepass-st/caliber-flex-5b with Transformers:

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

pipe = pipeline("text-classification", model="onepass-st/caliber-flex-5b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("onepass-st/caliber-flex-5b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use onepass-st/caliber-flex-5b 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 onepass-st/caliber-flex-5b:Q8_0
# Run inference directly in the terminal:
llama cli -hf onepass-st/caliber-flex-5b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf onepass-st/caliber-flex-5b:Q8_0
# Run inference directly in the terminal:
llama cli -hf onepass-st/caliber-flex-5b:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf onepass-st/caliber-flex-5b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf onepass-st/caliber-flex-5b:Q8_0

Use Docker

docker model run hf.co/onepass-st/caliber-flex-5b:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use onepass-st/caliber-flex-5b with Ollama:
```
ollama run hf.co/onepass-st/caliber-flex-5b:Q8_0
```
Unsloth Desktop

How to use onepass-st/caliber-flex-5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onepass-st/caliber-flex-5b:Q8_0

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": "onepass-st/caliber-flex-5b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use onepass-st/caliber-flex-5b with Docker Model Runner:
```
docker model run hf.co/onepass-st/caliber-flex-5b:Q8_0
```

Lemonade

How to use onepass-st/caliber-flex-5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull onepass-st/caliber-flex-5b:Q8_0

Run and chat with the model

lemonade run user.caliber-flex-5b-Q8_0

List all available models

lemonade list

Hermes Agent

How to use onepass-st/caliber-flex-5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onepass-st/caliber-flex-5b:Q8_0

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 onepass-st/caliber-flex-5b:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use onepass-st/caliber-flex-5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onepass-st/caliber-flex-5b:Q8_0

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 "onepass-st/caliber-flex-5b:Q8_0" \
  --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"

Caliber Flex 5B by OnePass

Decision-only model: no chat, no completions. You send a text plus questions, it returns picks with calibrated probabilities.

Exactly 5,000,000,000 parameters: Qwen3.5-4B-Base (Apache-2.0) depth-upscaled with 4 grafted top layers, trained LoRA r32, two-layer decision head (2087→984) with fitted temperature T=1.548. Counted, not rounded. Forecast reading taught by a TimesFM 3.0 teacher (non-commercial). English + Russian.

Files

File	What
`caliber-flex-5b-Q8_0.gguf`	Backbone + LoRA, Q8_0 quant. Generative/embedding use (chat, RAG).
`hybrid_adapter.pt`	Decision head + LoRA + temperature. Needed for decisions.
`merged/`	Full bf16 transformers model (backbone + LoRA merged).
`infer.py`	Standalone decisions, works offline.
`Modelfile`	Ollama import for the GGUF.

The GGUF alone does not answer decisions — the scoring head lives in hybrid_adapter.pt and runs through infer.py (transformers). The GGUF is the same backbone for open use: chat, embeddings, evals.

Decisions (transformers)

pip install torch transformers peft
python infer.py --state "Headline: Markets rally on rate cut hopes." \
  --type choice --options World Sports Business Sci/Tech
python infer.py --state "Что лучше?" \
  --type choice --options "Дыня" "Арбуз"

{
  "model": "caliber-flex-5b",
  "choice": "Business",
  "probabilities": {"World": 0.05, "Sports": 0.02, "Business": 0.88, "Sci/Tech": 0.05},
  "confidence": 0.84,
  "route_to_human": false
}

Three question types: choice (one of N), noul (yes/no probability), score (ordered levels, answered with the mean). No evidence in the state → flat probabilities and "route_to_human": true.

Metric	Value
Held-out accuracy	0.815
Brier	0.068
ECE	0.060
Temperature	1.548

NoulXP bench (noulxp bench, home i5-4250U CPU, Q8_0, concurrency 1):

Metric	Value
req/s	0.01
decisions/s	0.04
p50	68.1 s
errors	0

NoulXP conformance (conformance-5b.jsonl, our code on the NoulXP 0.1 request set): 52 cases, 91 questions, 0 errors.

GGUF (Ollama / llama.cpp)

ollama create caliber-flex-5b -f Modelfile
ollama run caliber-flex-5b

Ask it who it is and it answers itself — the identity is in the weights, no system prompt involved.

Notes

About 9 GB VRAM in bf16 for the transformers path; CPU runs, slowly. 8k context inherited from training. Calibrated on the sets above (acc 0.815, Brier 0.068, ECE 0.060) — re-check thresholds on your own data before automating. Non-commercial only (TimesFM teacher inside), and the caliber-flex-5b by OnePass identity stays in served responses.

Downloads last month: 67

GGUF

Model size

5B params

Architecture

qwen35

Hardware compatibility

8-bit

Model tree for onepass-st/caliber-flex-5b

Base model

Qwen/Qwen3.5-4B-Base

Quantized

(34)

this model