Buckets:
| license: other | |
| base_model: MiniMaxAI/MiniMax-M3 | |
| tags: [mlx, vmlx, jang, reap, awq, moe, code, multimodal, minimax-m3, apple-silicon] | |
| pipeline_tag: text-generation | |
| <p align="center"><img src="./vmlx-logo.png" alt="vMLX" width="150"></p> | |
| <h1 align="center">MiniMax-M3-REAP22-Coder</h1> | |
| <p align="center"><b>A JANG-quantized MiniMax-M3 — coding/agentic + multimodal — for the <a href="https://mlx.studio">vMLX</a> engine (Apple Silicon / MLX).</b></p> | |
| > ⚠️ **Requires vMLX engine v1.5.67 or newer.** | |
| > This is a **JANG-format** model (JANG affine-mixed + **AWQ** quantization, **REAP** expert pruning, and the | |
| > MiniMax-M3 MSA / Lightning-Indexer runtime). It will **NOT** load with `transformers`, `vLLM`, or generic MLX | |
| > loaders — it needs vMLX's JANG loader + the M3 runtime. **Coder support lands in vMLX ≥ 1.5.67.** | |
| ## What is a JANG model? | |
| **JANG** is vMLX's quantization + packing format: mixed-precision **affine** quantization (per-projection bit | |
| widths) + **AWQ** activation-aware scaling + **REAP** expert pruning, described by a `jang_config.json`. Weights | |
| stay quantized in GPU memory and are loaded by vMLX's JANG loader. Because the format **and** the MiniMax-M3 | |
| runtime (MSA dual-cache, Lightning Indexer, partial RoPE, vision tower) are vMLX-specific, **these models run | |
| only on vMLX ≥ 1.5.67.** | |
| ## Run it | |
| 1. Install/update **vMLX 1.5.67+** — https://mlx.studio (or `pip install -U vmlx`). | |
| 2. App: **Server → New Session →** pick/download this model **→ Start →** chat. | |
| 3. CLI: `vmlx-engine serve JANGQ-AI/MiniMax-M3-REAP22-Coder --reasoning-parser minimax_m3 --tool-call-parser minimax_m3` | |
| ## Highlights | |
| - **Coding: HumanEval pass@1 = 100%** (81/81 on a scrambled half of HumanEval, first-sample) — pass@5 = 1.000. | |
| - **Arithmetic/reasoning recovered** vs the base REAP quant (with reasoning enabled): ~7/7 on a 7-task probe. | |
| - **Multimodal (vision) kept.** ~107 GB on disk. | |
| ## Build | |
| - **Base:** MiniMaxAI/MiniMax-M3 (60 layers, MoE, MSA Lightning Indexer, GQA, partial RoPE). | |
| - **REAP pruning:** keep **100/128** routed experts per MoE layer (22% pruned), saliency-scored. | |
| - **JANG affine quant (group_size 64):** routed gate/up = **2-bit + AWQ pre-scaling**, down = 2-bit; shared | |
| experts 6-bit; attention 8-bit; embeddings 6-bit; lm_head 8-bit; Lightning Indexer + norms FP16; vision 8-bit. | |
| - **"Floor" expert recipe:** protect the proven coding experts (coding saliency) + add top math experts, so | |
| coding stays intact while math improves. | |
| - **Calibration:** Vera (agentic-coder) dominant + GSM8K (math reasoning). | |
| ## Attribution | |
| - Base model: **MiniMaxAI/MiniMax-M3** | |
| - Expert pruning: **REAP** (Cerebras, ICLR 2026, arXiv:2510.13999) | |
| - **Vera agentic-coder calibration dataset + evaluation/testing: [@hornsman1](https://huggingface.co/hornsman1) (hornsan1 on GitHub)** | |
| - Additional math-reasoning calibration: GSM8K | |
| - Quantization & runtime: **JANG / vMLX** | |
| ## Credits | |
| - Vera dataset & model testing: **@hornsby_andrew** ([hornsan1](https://github.com/hornsan1) on GitHub) | |
Xet Storage Details
- Size:
- 3.04 kB
- Xet hash:
- e482a8192aa63c94a5e8ee24f5d1f39b5599aec5d14cc5e07a2c8128dc6843fc
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.