--- title: jebadiah-27b-MLX canonical_url: "https://www.modelscope.ai/models/JasonBrashear/jebadiah-27b-MLX" md_url: "https://www.modelscope.ai/models/JasonBrashear/jebadiah-27b-MLX.md" repository: JasonBrashear/jebadiah-27b-MLX last_updated: 2026-09-29 license: apache-2.0 pipeline_tag: text-classification tasks: - text-classification base_model: - JasonBrashear/jebadiah-27b base_model_relation: quantized parameters: 11.8B tensor_type: - BF16 - U32 library_name: - mlx - safetensors language: - en downloads: 4 stars: 0 tags: - mlx - decision-model - system-one - typed-decisions - calibrated-probabilities - ainode --- # jebadiah-27b-MLX > jebadiah-27b-MLX - An open-source model by JasonBrashear on ModelScope. Mirror of huggingface.co/frontier-infra/jebadiah-27b-MLX. The Hugging Face repo is the source of truth: https://huggingface.co/frontier-infra/jebadiah-27b-MLX. Code and the standalone… JasonBrashear/jebadiah-27b-MLX is a 11.8B-parameter text-classification model on ModelScope. licensed under apache-2.0. derived from JasonBrashear/jebadiah-27b. - **Repository**: JasonBrashear/jebadiah-27b-MLX - **License**: apache-2.0 - **Tasks**: text-classification - **Parameters**: 11.8B - **Base model**: JasonBrashear/jebadiah-27b - **Tags**: mlx, decision-model, system-one, typed-decisions, calibrated-probabilities, ainode - **Downloads**: 4 - **Stars**: 0 - **Last updated**: 2026-09-29 Source: https://www.modelscope.ai/models/JasonBrashear/jebadiah-27b-MLX --- # Jebadiah 27B MLX > Mirror of huggingface.co/frontier-infra/jebadiah-27b-MLX. The Hugging Face repo is the source of truth: [https://huggingface.co/frontier-infra/jebadiah-27b-MLX](https://huggingface.co/frontier-infra/jebadiah-27b-MLX). Code and the standalone server: [github.com/getainode/jebadiah](https://github.com/getainode/jebadiah). MLX builds of [Jebadiah 27B](https://huggingface.co/frontier-infra/jebadiah-27b) for Apple silicon, one folder per precision (`8bit/`, `4bit/`, group size 64). Jebadiah answers a typed question (choice, noul or score) with a probability for every option, read from one forward pass. Nothing is generated. Code, trainer and evals: [getainode/jebadiah](https://github.com/getainode/jebadiah). **Results and docs** - Project site, with every result and how to run the models: [jebadiah.ai](https://jebadiah.ai). - [Decision Index 0.2.1](https://huggingface.co/spaces/multimodalart/jev-decision-index): Jebadiah 27B scores 54.67, #5 of 67 open models (as of 2026-09-26). This is the board's own number; the maintainer validated my run and put it on the leaderboard. [Run record](https://huggingface.co/datasets/frontier-infra/jebadiah-decision-index-results/tree/main/runs/jebadiah-27b-1c0d794f). - JevBench v1.4.2: on its 231 public items, run through its own harness, Jebadiah 27B scores 0.866, the same as Jev 1.13.0. This is my own run on the public items, not the official board, which also uses sealed items. [Details and caveats](https://github.com/getainode/jebadiah#where-we-stand-on-jevbench). - All sizes: the [Hugging Face collection](https://huggingface.co/collections/frontier-infra/jebadiah-open-system-one-decision-models-6ab80765ddd3fa0b3eba5213), mirrored on [ModelScope](https://www.modelscope.ai/profile/JasonBrashear). **Which one should I use?** For local use, start with [Jebadiah 9B v2 GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF). On Apple silicon, use an MLX build: [27B](https://huggingface.co/frontier-infra/jebadiah-27b-MLX), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2-MLX) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX). For vLLM or fine-tuning, use the full weights: [27B](https://huggingface.co/frontier-infra/jebadiah-27b), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2). Setup for every runtime, and for JDE: [Run Jeb locally](https://github.com/getainode/jebadiah/blob/main/docs/run-locally.md). ## Files Every file was checked on the 260 held-out questions the merged weights were checked on, and compared with the merged bf16 weights and with the training run's own eval records. | File | Size | Same answer as bf16 | Same as the run | choice + noul | score | Prob. diff median / max | |---|---:|---:|---:|---:|---:|---:| | `8bit/` | 28.6 GB | **259 / 260** | 258 / 260 | 173 / 173 | 85 / 87 | 0.003 / 0.050 | | `4bit/` | 15.1 GB | **248 / 260** | 247 / 260 | 169 / 173 | 78 / 87 | 0.023 / 0.177 | | *bf16 weights* | 55.6 GB | | 259 / 260 | 173 / 173 | 86 / 87 | 0.002 / 0.019 | Which one: `8bit` if your Mac has the memory; `4bit` when it does not. A folder needs about its own size in unified memory, plus about 1 GB for a 2k-token prompt. **`4bit` changes 12 of 260 answers** against bf16 (8 on score questions) and moves probabilities more (median 0.023, max 0.18). Use it only when a larger build does not fit. ## Run it The script renders the prompt exactly as AINode does, runs one forward pass with mlx-lm, multiplies the last hidden state by the option labels' output-head rows in fp32 and applies `temperatures.json` (choice 1.2321, noul 1.297, score 0.7558). Needs mlx-lm 0.31 or newer (qwen3_5 support). ```bash pip install "mlx-lm>=0.31" hf download frontier-infra/jebadiah-27b-MLX --include "8bit/*" --include "scripts/*" --include temperatures.json --local-dir jebadiah-27b-MLX cd jebadiah-27b-MLX python scripts/decide_mlx.py --model 8bit --request scripts/example-request.json ``` `--no-temperatures` returns the raw probabilities. On `example-request.json` (8bit/): ```json { "route": {"type": "choice", "choice": "billing", "confidence": 0.646831, "probabilities": {"billing": 0.764554, "support": 0.03266, "sales": 0.202786}}, "urgent": {"type": "noul", "noul": 0.200315} } ``` ## How it was measured Jevals PubMedQA, Banking77 (77 options) and HelpSteer2, plus Nimble: the merge check's fixed sample (seed 20260925), the run's option order and the run's temperatures, so the probability differences compare like with like (the shipped temperatures.json since `1c0d794f` uses 0.7558 for score; top picks do not depend on it). "Same answer" is the top option; "prob. diff" is the largest change on any option against the run's CUDA record. Records: `eval/agreement-*.json`. ## License Apache-2.0, as the base model. Made in Texas.