Run locally / Model details

Xor 26B-A4B

26B text model.

Recipe ready · unverifiedtext#9 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.

VariantPrecisionRuntimeBenchmarkedInstall recipeMinimum / recommended VRAMRAMDiskPlatformsExpected speed
bf16-sglang-author-bundlebf16See model cardYesRecipe ready · unverified64 GB / 64 GB68 GB51.64 GBlinux-nvidiaAbout 59 ms p 50 per decision (raw, serial) on the measured GPU; GPU UNVERIFIED. 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-sglang-author-bundlebf16
Runtime
See model card
Install recipe
Recipe ready · unverified
VRAM
64 GB minimum / 64 GB recommended
RAM
68 GB
Disk
51.64 GB
Platforms
linux-nvidia
Expected speed
About 59 ms p 50 per decision (raw, serial) on the measured GPU; GPU UNVERIFIED. 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 xor-26b-a4bChecks 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.

  1. 1curl -fsSL https://decisionmodels.io/local/install.sh | sh && export PATH="$HOME/.local/bin:$PATH"
  2. 2dm-local install xor-26b-a4b

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":"xor-26b-a4b","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 xor-26b-a4b

Model terms

Licence details

apache-2.0Commercial use: yes

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

Model card

The author has not published where the training data came from. We found no statement or evidence that it was distilled from Jev outputs.

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.

Xor 26B-A4B local setup — Decision Models