Built and tested on Apple M5 Max (128 GB) · upstream revision JEV-35B (a5d0d58)
A 8-bit MLX build of autotrust/JEV-35B for Apple Silicon, with vision. 36 GB. Released 19 October 2026.
JEV-35B is AutoTrust AI's System 1 decision model, a fine-tune of Qwen3.5-35B-A3B (35 B parameters, about 3 B active per token). Each call is one typed question about a state (text, JSON or images), answered in one forward pass with a calibrated probability for every allowed option: choice (2 to 256 options you supply), noul (yes / no) or score (0 to 5). It classifies, routes, gates and ranks; it does not chat or generate text.
This build: Every layer at 8 bits (affine, group size 64), except the vision tower and the router gates, which stay in bf16. Recommended for Macs with 48 GB or more. Effectively the original model: it picks the same answer on 228 of 231 decisions and its probabilities drift by a KL of 0.002 on average.
Published by NetProjects (Internet Projects Ltd). Not affiliated with AutoTrust AI.
pip install "git+https://github.com/internet-projects/autotrust-jev35b-mlx"
import jev_mlx
jev = jev_mlx.load("netprojects/AutoTrust-JEV-35B-mlx-8bit")
r = jev.decide("choice",
state="Customer message: my card was charged twice for the same order.",
question="Which team should handle this ticket?",
options=["billing", "shipping", "technical support", "account security"])
print(r["choice"], r["probabilities"])
r = jev.decide("noul", state=["Photo from the warehouse:", {"image": "shelf.jpg"}],
question="Is any box on the shelf damaged?")
print(r["probabilities"][1]) # P(true)
Or as a server with the same /v1/decide fields as autotrust's own:
python -m jev_mlx serve netprojects/AutoTrust-JEV-35B-mlx-8bit --port 8000
curl localhost:8000/v1/decide -H 'Content-Type: application/json' -d '{"kind": "noul",
"state": "Order 1182 arrived with a cracked screen.", "question": "Does the customer report damage?"}'
autotrust-jev35b-mlx reproduces the read-out of autotrust's serve_decide.py: the answer-slot logits at the last position, plus the decision-head bias, divided by the per-kind temperature in calibration.json. Both files ship in this repository.
231 decisions built from the JevBench public set, each compared with the original bf16 weights (converted to MLX without quantization) on a MacBook Pro M5 Max:
| build | size | memory in use | same top answer | probability drift, KL mean / p95 | warm median (p95) per decision |
|---|---|---|---|---|---|
| 8-bit | 36 GB | 37.7 GB | 228 / 231 | 0.002 / 0.009 | 164 ms (1,037 ms) |
| 4-bit mixed | 21 GB | 21.6 GB | 225 / 231 | 0.004 / 0.021 | 109 ms (246 ms) |
| 3-bit mixed | 17 GB | 17.6 GB | 224 / 231 | 0.012 / 0.056 | 99 ms (234 ms) |
scripts/check.py, scripts/vision_check.py, scripts/speed.py).For the model's own benchmarks (Decision Index, vision, ERQA, computer use), see the original model card.
Model: autotrust/JEV-35B by AutoTrust AI (Apache-2.0, the same license as the original), a fine-tune of Qwen/Qwen3.5-35B-A3B (Apache-2.0). Converted with mlx-vlm. Code in autotrust-jev35b-mlx: Apache-2.0. Port by Paris Michalas, Partner, NetProjects (Internet Projects Ltd). Not affiliated with AutoTrust AI.
More NetProjects MLX builds: NetProjects MLX builds collection · all models at huggingface.co/netprojects
model-00004-of-00008.safetensors 5.4 GBmodel-00006-of-00008.safetensors 5.4 GBmodel-00002-of-00008.safetensors 5.4 GBmodel-00005-of-00008.safetensors 5.4 GBmodel-00003-of-00008.safetensors 5.4 GBmodel-00001-of-00008.safetensors 5.3 GBmodel-00007-of-00008.safetensors 5.0 GBmodel-00008-of-00008.safetensors 540 MBautotrust/JEV-35B