caliber-flex-5b: open AI decision model by OnePass

Q: How do I run caliber-flex-5b?

Pull the weights with systemone pull onepass-st/caliber-flex-5b and load them with the runtime named in the manifest.

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

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.

Playground

Build a request for onepass-st/caliber-flex-5b. The form and the JSON are the same object; the response panel shows the shape every System One server returns.

Input

StateThe context the questions are asked about. Up to the model's context length.

A yes/no question. The answer is one probability that the condition holds.

Instructions

Response

Placeholder values, in the shape a run returns.

safenoul7%

This model doesn't answer live here. Send this request to your own server for this model; every System One server speaks this shape.

Call it

curl https://api.systemonemodels.ai/v1/systemone \
  -H "Authorization: Bearer $SYSTEMONE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"onepass-st/caliber-flex-5b","state":"Task: clean up inactive accounts before the quarterly report.\nProposed tool call: delete_rows(table=\"customers\", where=\"last_login < 2023-01-01\")\nContext: the customers table is production; there is no backup newer than Friday.","questions":{"safe":{"type":"noul","instructions":"Is this action safe to run without a human approving it first?"}}}'

Providers

Where this model runs today. Call the provider directly or run the weights yourself.

Provider	Status	Input	Output	Context	Link
Your own hardware	Open weights	Free	Free	—	`systemone pull onepass-st/caliber-flex-5b`

Pricing

Availability: Open weights
Licence: caliber-flex-non-commercial-1.0
Hosted API: None recorded. Pull the weights and run it yourself.

Pulling and running the weights costs nothing beyond your own hardware; the licence above says what you may do with them.

Performance

No evaluation has been published for this model yet.

caliber-flex-5b-Q8_0.gguf92832094.6 GB
hybrid_adapter.ptb4d0ab141 MB
infer.pyef1a7314.5 kB
LICENSE96af7051.0 kB
Modelfile75070c2176 B
README.md8d7d1a62.7 kB
systemone.yaml60f1f3b489 B

config.json5d4a8592.0 kB
merge_info.json3da5f03221 B
model-00001-of-00005.safetensors73e8ccc1.9 GB
model-00002-of-00005.safetensors65dec351.9 GB
model-00003-of-00005.safetensorsff376271.9 GB
model-00004-of-00005.safetensorsef2d5fe1.9 GB
model-00005-of-00005.safetensorscfbf5d61.1 GB
model.safetensors.index.jsonef7237737 kB
tokenizer_config.json20b487e1.4 kB
tokenizer.jsona5cd97319 MB

Every file resolves through a stable path — /v1/models/onepass-st/caliber-flex-5b/resolve/0.1.0/<path> — while the object underneath is content-addressed and shared with every other version that holds the same bytes. API reference.

Model tree

Every ancestor down to this model, then what was built on it, wherever each one lives.

Activity

Downloads81

Stars0

Versions1

Built with it0

Latest version: 0.1.0
Updated: Oct 29, 2026
Added to the registry: Oct 10, 2026

Documentation

The HTTP API — every endpoint the website and CLI use.
The CLI — pull this model with systemone pull onepass-st/caliber-flex-5b.
systemone.yaml — what the manifest below records.

systemone.yaml

{
  "spec_version": "0.1",
  "model": "caliber-flex-5b",
  "namespace": "onepass-st",
  "category": "system-one",
  "architecture": "llm",
  "base_model": "qwen/qwen3.5-4b-base",
  "base_model_source": "huggingface",
  "license": "other",
  "license_name": "caliber-flex-non-commercial-1.0",
  "summary": "Caliber Flex 5B by OnePass. Decision-only model, exactly 5,000,000,000 parameters.",
  "tags": [
    "decision-model",
    "calibrated",
    "qwen3_5",
    "timesfm-distilled",
    "onepass",
    "gguf"
  ],
  "capabilities": [
    "choice",
    "noul",
    "score"
  ],
  "runtime": {
    "framework": "safetensors",
    "entrypoint": null,
    "python": null,
    "hardware": "cpu"
  },
  "artifacts": [],
  "evaluation": null,
  "parameters": null,
  "context_length": null,
  "hub_repo": null,
  "released": null,
  "availability": "open-weights",
  "hosted": null
}

View raw metadata

FAQ

What does caliber-flex-5b decide?

It answers 3 kinds of question: choice picks one option from a list you give it; noul returns the probability that a condition holds; score rates the state on a scale you define. Every answer is a typed value with a probability, never free text.

How do I run caliber-flex-5b?

Pull the weights with systemone pull onepass-st/caliber-flex-5b and load them with the runtime named in the manifest.

Can I use caliber-flex-5b commercially?

It is published under caliber-flex-non-commercial-1.0. Read the licence before shipping; the model card may add terms of its own.

What is caliber-flex-5b built on?

Its base model is qwen/qwen3.5-4b-base, a llm architecture. The Model tree section shows the whole chain.

How much can caliber-flex-5b read at once?

The publisher has not recorded a context length.

How do I link to caliber-flex-5b?

This page is https://systemonemodels.ai/onepass-st/caliber-flex-5b. Its metadata is at https://api.systemonemodels.ai/v1/models/onepass-st/caliber-flex-5b and a Markdown summary for agents at https://systemonemodels.ai/onepass-st/caliber-flex-5b.md.

OnePass: caliber-flex-5b

Caliber Flex 5B by OnePass

Files

Decisions (transformers)

GGUF (Ollama / llama.cpp)

Notes

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ

OnePass: caliber-flex-5b

Caliber Flex 5B by OnePass

Files

Decisions (transformers)

GGUF (Ollama / llama.cpp)

Notes

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ