# Nimble model sizes and sources

> Nimble is Bespoke Labs' 9B decision model, tuned from Qwen3.5-9B. Its 2,676 training examples are public, and Ollama supports it.

Updated 2026-11-04 (Australia/Adelaide)

By Bespoke Labs · Released: 2026-09-18 · OPEN

A 9B decision model, LoRA-tuned from Qwen3.5-9B, with its 2,676 training examples published. One of the first two models in Ollama's decision support. Bespoke Labs followed with hosted [Nimble](<https://decisionmodels.ai/models/nimble>) v4 (9B) and v4-max (27B) on 13 Oct 2026.

## Facts

- Size: 9B
- Licence: Apache 2.0
- Run it: ollama pull [nimble](<https://decisionmodels.ai/models/nimble>)

## Claims and sources

- **VENDOR-REPORTED**: Matches 90.1% of reference labels on 324 held-out examples, against 93.2% for [Jev](<https://decisionmodels.ai/models/jev>) 1.13 [source](<https://github.com/bespokelabsai/nimble>)

## Links

- [Source: GitHub](<https://github.com/bespokelabsai/nimble>)
- [Source: Ollama](<https://ollama.com/library/nimble>)
- [Source: Hugging Face](<https://huggingface.co/bespokelabs/Bespoke-Nimble-9B>)
- [Source: Nimble README](<https://github.com/bespokelabsai/nimble>)

## Related projects

### Nimble and Laya play Slay the Spire

[Nimble and Laya play Slay the Spire](<https://decisionmodels.ai/projects#project-slay-the-spire>)

[Source: MindrLabs/typed-decision-slay-the-spire](<https://github.com/MindrLabs/typed-decision-slay-the-spire>)

Runs Bespoke Nimble-9B and three [Laya](<https://decisionmodels.ai/models/laya>) checkpoints as players over the same 200 seeds of a headless Slay the Spire simulator, zero-shot and fine-tuned. The results are the authors' own.

- Creator: MindrLabs

- Stars: 2

- Licence: MIT

- Model: [Nimble](<https://decisionmodels.ai/models/nimble>), [Laya](<https://decisionmodels.ai/models/laya>)

- Tags: game, benchmark

### Offline browser agent on Nimble

[Offline browser agent on Nimble](<https://decisionmodels.ai/projects#project-nimble-pilot>)

[Source: jinyoung/nimble-pilot](<https://github.com/jinyoung/nimble-pilot>)

A macOS app whose browser agent makes every choice, such as which element to click, as one classification by Nimble-9B running locally in Ollama. Low-confidence calls go to the person.

- Creator: jinyoung

- Stars: 0

- Licence: Apache-2.0

- Model: [Nimble](<https://decisionmodels.ai/models/nimble>)

- Tags: browser, agent

### Thunderbird email tagging that learns

[Thunderbird email tagging that learns](<https://decisionmodels.ai/projects#project-kestrel>)

[Source: sarath/krestel](<https://github.com/sarath/krestel>)

A Thunderbird extension that tags your email with decision models served by Ollama's /v1/systemone endpoint, such as [Tev1](<https://decisionmodels.ai/models/tev1>) 0.8B, [Tev1](<https://decisionmodels.ai/models/tev1>) 4B or [Nimble](<https://decisionmodels.ai/models/nimble>), and keeps learning from the tags you add by hand.

- Creator: sarath

- Stars: 0

- Licence: MIT

- Model: [Tev1](<https://decisionmodels.ai/models/tev1>), [Nimble](<https://decisionmodels.ai/models/nimble>)

- Tags: email, local

### Decision models as tool routers, measured

[Decision models as tool routers, measured](<https://decisionmodels.ai/projects#project-decision-agent-lab>)

[Source: Daewooki/decision-agent-lab](<https://github.com/Daewooki/decision-agent-lab>)

Calls [Jev](<https://decisionmodels.ai/models/jev>), OpenAI's [Decisions API](<https://decisionmodels.ai/models/openai-decisions>), Upstage [Solar Decide](<https://decisionmodels.ai/models/solar-decide>) and local Ollama models through one interface and logs version, latency, tokens and cost. On picking the right one of 12 tools for 40 Korean and English requests, the maker measured [Jev](<https://decisionmodels.ai/models/jev>) 1.13 at 40 of 40 and OpenAI Decisions at 0.90, against 0.85 for a generative model choosing directly.

- Creator: Daewooki

- Stars: 0

- Licence: MIT

- Model: [Jev](<https://decisionmodels.ai/models/jev>), [Decisions API](<https://decisionmodels.ai/models/openai-decisions>), [Solar Decide](<https://decisionmodels.ai/models/solar-decide>), [Nimble](<https://decisionmodels.ai/models/nimble>)

- Tags: agent, benchmark