Labqoat · Download verified

qev 0.8B · Labqoat

Sort messages or select a next action locally using answer choices you define. This is Labqoat’s model; similarly named Qev downloads from other authors are separate.

First reviewed 2026-10-21 · Checked 2026-11-03. The launch date has not been confirmed.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.

Runs onYour hardwareHardware and setup costs apply

Documented capacityNot verifiedSee input limits below

What you can use today

You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.

Exact download ID: labqoat/qev-0.8b. The current SG50 revision adds image input through its supplied runtime. Images are resized to at most 448×448 pixels; image support uses the base vision encoder without specialized image training. Use separate evaluation for each question on image or closely related requests.

Apache 2.0-labelled weights with CUDA, CPU, MLX and GGUF paths. The publisher flags mixed training-data terms, weak scoring, difficult long inputs and unreliable abstention. Its fitted probabilities need calibration on your own examples. Pin the revision: the current artifact differs from the earlier text-only release.

A dependable task-specific input limit is not established: the decision configuration allows one million state tokens while the inherited model configuration lists 262,144 positions. Long-input accuracy needs separate testing.

Output: Yes/no probabilities, choices and ordered scores; no generated explanation. Compare decision models, limits and input costs ↗

No hosted rate. Publisher tests and speed figures are not independent measurements. Repository first created October 20; pin the exact revision because tokenizer and weights can change.

Provider release and specifications ↗

Check availability and plans ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.

Compare caching and long-context costs ↗