Update README with Q8 engine requirements and upload status notice

README.md

@@ -15,15 +15,54 @@ tags:
 
 # Qwen3.8-27B-Splash-HQ (Native 8-bit)
 
-This repository contains the uncompressed native 8-bit weights of **Qwen3.8-27B** with built-in Multi-Token Prediction (MTP) heads, optimized for the **Splash** inference engine on Apple Silicon.
-
-## Performance vs MTPLX & MLX on Apple Silicon
-
-| Model | Format | Decode Speed (tok/s) | Speedup vs Stock AR |
-| :--- | :--- | :---: | :---: |
-| **Qwen3.8-27B-Splash-HQ** | **Native 8-bit + MTP** | **36.9 t/s** (peak 54.8) | **3.73x** |
-| Splash-Q8 | Compressed 8-bit | 36.5 t/s (peak 52.7) | 3.69x |
-| Splash-Q4 | 4-bit + MTP | 60.7 t/s (peak 83.3) | 6.13x |
-| MTPLX-Optimized-Quality | 8-bit + MTP D3 | 26.5 t/s (peak 28.8) | 2.68x |
-| MLX-Community 8bit | 8-bit Stock AR | 9.9 t/s | 1.00x |
-| llama.cpp Q8_0 GGUF | Q8_0 Stock AR | 9.9 t/s | 1.00x |
+> [!IMPORTANT]
+> ### ⚠️ Runtime Package Compatibility & Upload Status
+> 1. **Weight Upload in Progress:** The 27 GB model weight files are currently streaming to this repository (~35% complete, ETA ~1.5h). The repository initially only contained tokenizer configurations and metadata.
+> 2. **Engine Requirements:** This model is packed in the **`splash-packed-q8` (schema_version 5)** format developed for high-precision Apple Silicon evaluation. 
+>    * Official upstream Splash 1.0 (`incoai/splash`) only recognizes 4-bit formats (`splash-packed-q4`, schema 3/4) and will reject Q8 packages with `repository is not a supported Splash runtime package`.
+>    * To run this model, use the Q8-enabled Metal runtime fork available at:
+>      👉 **[https://github.com/npanj/qwen3.8-27b-apple-silicon-eval](https://github.com/npanj/qwen3.8-27b-apple-silicon-eval)**
+
+---
+
+## Overview
+
+This repository contains the uncompressed native 8-bit weights of **Qwen3.8-27B** with built-in Multi-Token Prediction (MTP) heads, optimized for high-throughput speculative decoding on Apple Silicon.
+
+All 64 layers are packed with true uncompressed 8-bit tiled weights (`MDFL0008`), preserving exact associative reasoning while running speculative verification via Splash's compiled Metal kernel pipeline.
+
+## Performance Benchmark vs Other Engines (Apple M5 Pro, 64 GiB)
+
+| Model / Engine | Format | Speculative Scheme | Decode Speed (tok/s) | Speedup vs Stock AR |
+| :--- | :--- | :--- | :---: | :---: |
+| **Qwen3.8-27B-Splash-HQ** | **Native 8-bit** | **Splash Metal MTP** | **36.9 t/s** (peak 54.8) | **3.73x** |
+| Splash-Q8 | Transcoded 8-bit | Splash Metal MTP | 36.5 t/s (peak 52.7) | 3.69x |
+| Splash-Q4 | 4-bit | Splash Metal MTP | 60.7 t/s (peak 83.3) | 6.13x |
+| MTPLX-Optimized-Quality | 8-bit | MTPLX DraftCore D3 | 26.5 t/s (peak 28.8) | 2.68x |
+| MLX-Community 8bit | 8-bit | None (Autoregressive) | 9.9 t/s | 1.00x |
+| llama.cpp Q8_0 GGUF | Q8_0 | None (Autoregressive) | 9.9 t/s | 1.00x |
+
+---
+
+## How to Run
+
+### Step 1: Clone the Q8 Splash Engine
+```bash
+git clone https://github.com/npanj/qwen3.8-27b-apple-silicon-eval.git
+cd qwen3.8-27b-apple-silicon-eval
+```
+
+### Step 2: Serve the Model
+```bash
+python server/server.py \
+  install/models/incoai/Qwen3.8-27B-Splash-HQ/target \
+  install/models/incoai/Qwen3.8-27B-Splash-HQ/draft \
+  --tokenizer install/models/incoai/Qwen3.8-27B-Splash-HQ/tokenizer \
+  --model incoai/Qwen3.8-27B-Splash-HQ \
+  --port 8000
+```
+
+### Step 3: Connect Coding Agents (Oh My Pi / Claude Code)
+```bash
+omp --model splash/incoai/Qwen3.8-27B-Splash-HQ
+```