nimble:9b
2 TagsUpdated 9B params8192 contextEnglishApache-2.0by Bespoke Labs
Bespoke-Nimble-9B v2 (LoRA on Qwen3.5-9B) with the author's temperature 2.18. Needs a 24 GB GPU.
9b
ollaya run nimble:9b --preset triage "I was charged twice for my subscription this month and want a refund."curl http://localhost:11435/api/decide \
-H "Content-Type: application/json" \
-d '{
"model": "nimble:9b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
}'# Already using a TypeSafe SDK? Set TYPESAFE_BASE_URL=http://localhost:11435 instead.
import requests
response = requests.post(
"http://localhost:11435/api/decide",
json={
"model": "nimble:9b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
},
)
answers = response.json()["answers"]
print(answers["department"]["choice"], answers["refund"]["noul"])const response = await fetch("http://localhost:11435/api/decide", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "nimble:9b",
state: "I was charged twice for my subscription this month and want a refund.",
questions: {
department: {
type: "choice",
instructions: "Which team should handle this?",
criteria: {
billing: "Payments, invoices and refunds",
technical: "Bugs, errors and outages",
account: "Login, profile and settings"
}
},
refund: {
type: "noul",
instructions: "Is the customer asking for a refund?"
}
}
}),
});
const { answers } = await response.json();
console.log(answers.department.choice, answers.refund.noul);Details
- graph78f7d8f5015d · 14 MB
onnx · nimble · 9B · fp32 - weightsdb6f444b43d3 · 5.3 GB
huggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00001-of-00004.safetensors - weights31c7d7e2dd5d · 5.3 GB
huggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00002-of-00004.safetensors - weights7ec36ba3a417 · 5.4 GB
huggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00003-of-00004.safetensors - weightsb62b0c4cd7e4 · 3.3 GB
huggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00004-of-00004.safetensors - weights1bd126be997b · 173 MB
huggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/adapter_model.safetensors - tokenizer06b9509352d2 · 20 MB
huggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/tokenizer.json - decision6abb22e62ff7 · 11 KB
{"engine": "onnx", "family": "nimble", "encoder": "", "layout": "nimble-codes-v1", …} - calibration185dcc039a5e · 306 B
{"temperature": [2.179, 2.179, 2.179]} - licenseff2de1e5553f · 10 KB
Bespoke-Nimble-9B-v2 by Bespoke Labs (https://huggingface.co/bespokelabs/Bespoke-Nimble-9B-v2)
Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.