decisio v0.8.0 on gemma-4-31B-it

31B text model.

Recipe ready · unverifiedtext#2 on JevBench (Capability, v1.6.1)

Hardware

Will it run on my machine?

Requirements are recorded per variant. A dash means the catalogue does not provide that value.

Variant	Precision	Runtime	Benchmarked	Install recipe	Minimum / recommended VRAM	RAM	Disk	Platforms	Expected speed
bf16-fp8-on-load-vllm	fp8-on-load (base bf16)	vLLM 0.30.0	Yes	Recipe ready · unverified	48 GB / 48 GB	80 GB	62.58 GB	linux-nvidia, wsl2-nvidia	About 47 ms p 50 per decision (raw, serial) on the measured GPU; the author reports 56 ms median on its own run. Provisioning class: RTX PRO 6000 96 GB; this names a memory class, not a latency measurement or confirmation of architecture compatibility. CPU/Mac speed is estimated only in separate portable variants.

bf16-fp8-on-load-vllmfp8-on-load (base bf16)

Runtime: vLLM 0.30.0
Install recipe: Recipe ready · unverified
VRAM: 48 GB minimum / 48 GB recommended
RAM: 80 GB
Disk: 62.58 GB
Platforms: linux-nvidia, wsl2-nvidia
Expected speed: About 47 ms p 50 per decision (raw, serial) on the measured GPU; the author reports 56 ms median on its own run. Provisioning class: RTX PRO 6000 96 GB; this names a memory class, not a latency measurement or confirmation of architecture compatibility. CPU/Mac speed is estimated only in separate portable variants.

dm-local plan decisio-gemma-4-31b-v080Checks memory, disk, platform, and runtime against the catalogue.

Quick start

Choose where to run it

Installer commands use the pinned model revision. Confirm the model terms before proceeding.

An install recipe is available, but it has not been verified by an install test.

1curl -fsSL https://decisionmodels.io/local/install.sh | sh && export PATH="$HOME/.local/bin:$PATH"
2dm-local install decisio-gemma-4-31b-v080

Call your endpoint

Use a local typed endpoint

The API accepts typed questions and returns typed answers with probabilities.

Request

curl http://127.0.0.1:8484/v1/systemone -H 'Content-Type: application/json' -d '{"state":"Mia owns a red bicycle.","questions":{"color":{"type":"choice","instructions":"Which color is the bicycle?","criteria":{"red":null,"blue":null}}}}'

Example output

{"id":"dec_…","model":"decisio-gemma-4-31b-v080","answers":{"color":{"type":"choice","choice":"red","confidence":0.97,"probabilities":{"red":0.97,"blue":0.03}}},"usage":{"input_tokens":64,"output_tokens":0,"decisions":1}}

Python

import json
import urllib.request
payload = {"state": "Mia owns a red bicycle.",
           "questions": {"color": {"type": "choice", "instructions": "Which color is the bicycle?", "criteria": {"red": None, "blue": None}}}}
request = urllib.request.Request("http://127.0.0.1:8484/v1/systemone", data=json.dumps(payload).encode(), headers={"Content-Type": "application/json"})
with urllib.request.urlopen(request, timeout=30) as response:
    result = json.load(response)
print(result["answers"]["color"])

Read the hosted API reference →

Uninstall

Remove the local files

Use the installer to stop the service and remove this model's downloaded files.

dm-local uninstall decisio-gemma-4-31b-v080

Model terms

Licence details

apache-2.0Commercial use: yes

Commercial use is allowed by the model’s listed licence.

Model card

The local installer has a separate free and commercial licence.

Troubleshooting

Common setup issues

Driver or CUDA version is too old

Update to a driver/runtime combination listed for the selected variant, then run dm-local plan again.

Out of memory

Choose a smaller quantised variant when one is listed, or use a remote GPU with enough recommended memory.

NVIDIA Container Toolkit is missing

Install and configure the NVIDIA Container Toolkit for your host before retrying the container runtime.

The port is already in use

Stop the service using port 8484 or configure a different local port, then rerun the self-test.

A download was interrupted

Run the install command again. Completed downloads resume when the artifact server supports range requests.

Checksum verification failed

Do not use the file. Remove the incomplete download and retry from the pinned official source.

Apple Silicon memory pressure

Close other memory-heavy apps and choose a smaller supported variant if the catalogue lists one.

WSL2 cannot see the GPU

Check the Windows GPU driver and WSL2 GPU support, then verify nvidia-smi inside the WSL distribution.

SSH or firewall blocks the endpoint

Keep the service on loopback and use an SSH tunnel. Avoid exposing the API port directly to the public internet.