--- license: apache-2.0 base_model: Qwen/Qwen3.8-27B tags: - text-generation - gguf - quantizer - autoround - architecture-aware - mamba - ssm - multi-token-prediction - mtp --- # Qwen3.8-27B-YMQ-MTP-GGUF > **Source Model:** [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) ### βš–οΈ An Architecture-Aware, AutoRound-Inspired Mixed Precision Layout This repository features advanced, custom architecture-aware quantizations of **Qwen3.8-27B** processed directly from official raw `BF16` source files using the custom **YMQ-Compiler (v2.0)** log-space framework. These builds natively support parallel multi-token prediction (MTP) speculation engines and utilize high-context optimization parameters tailored for demanding code development API execution environments (such as RooCode/Aider).

ZeroDigest YMQ Logo

--- ## πŸ“Š Quantization Preset Tier Details | Preset Tier | Total Size | Target Usage / Memory VRAM Profile | Cognitive Real-World Coding Quality | | :--- | :--- | :--- | :--- | | **`XXXS`** | ~9.8 GB | Absolute VRAM Squeeze / 12GB Card Lifeline | Massive structural quantization noise. Best restricted to low-context, single-turn instructions. Fits 12GB cards with context cache breathing room. | | **`XXS`** | ~11.0 GB | Max budget squeeze / For the desperate | High compression noise floor. Works for short scripts, prone to api calling degradation past 50k context size. | | **`XS`** | ~12.2 GB | Light workspace / Low-VRAM cache headroom | Balanced economy. Great text parsing consistency, minor context layout fatigue on long coding passes. | | **`M`** | ~14.0 GB | **The Ultimate Coding Sweet Spot (Recommended)** | **Elite logical stability.** Complete logic clarity. It crushes standard industry 4-bit alternatives. | | **`L`** | ~17.0 GB | Premium Single-GPU Processing / Heavy workloads | Near-lossless instruction formatting. Pristine multi-turn architecture safety. | | **`XL`** | ~19.0 GB | Maximum VRAM Fill / No Compromises | Mathematical saturation ceiling. Full precision logic tracks for massive multi-file codebase operations. | ## πŸ“‰ Perplexity Evaluation Metrics (WikiText-2) The following metrics demonstrate the mathematical quality preservation of the **YMQ-Compiler** log-space cluster analysis compared to standard linear quantization layouts. Tested natively via `llama-perplexity` over a 4096 context window using the official WikiText-2 test corpus. | Model Preset Variant | File Size | Perplexity Score (Lower is Better) | Cognitive Calibration Verdict | | :--- | :--- | :--- | :--- | | **`XXXS`**| ~9.8 GB | 7.7848 | Extreme VRAM economy boundary cliff. | | **`XXS`**| ~11.0 GB | 7.2565 | Isolated task profile fallback baseline. | | **`XS`** | ~12.2 GB | 8.2557 | Maximum budget compression cliff on intermediate layers. | | **`M` (Recommended)**| ~14.0 GB | **6.8413** | 🎯 **The Golden Architectural Sweet Spot** | | **`L`** | ~17.0 GB | 6.9791 | Minor cumulative network drift from background bloat. | | **`XL`** | ~19.0 GB | 6.8196 | Full mathematical saturation ceiling. | ### πŸ’‘ The Core Architectural Discovery Notice the dramatic performance leap between the `XS` and `M` presets. The **YMQ-Compiler** log-space algorithm automatically detects the true data signals on the newly updated Qwen 3.8 hybrid Attention/Mamba routing nodes. By shifting the quantization boundaries slightly in the **`M` preset**, the engine safely promotes the model's high-leverage logical spikes straight into full high-fidelity precision layers. This drops the perplexity score down to an elite **6.8413**β€”matching the raw reasoning power of the massive 19GB `XL` file while clawing back a clean **5 Gigabytes of VRAM overhead cache space** for your local agent environments! --- ## βš–οΈ YMQ vs. Uniform Quantization (The AutoRound Philosophy) Standard quantization pipelines apply a blunt, uniform bit-depth across every single layer in a model. This wastes valuable VRAM on silent background layers while starving critical logic anchors of necessary precision. The **YMQ-Compiler** implements a philosophy similar to advanced weight-tuning frameworks like **Intel's AutoRound**: * **Targeted Bit Allocation:** It strips bits away from low-leverage background tensors and automatically re-allocates that saved VRAM budget straight into full high-fidelity shields for the model's highest cognitive spikes and boundary pathways. * **Instant Optimization:** Instead of running heavy, days-long optimization training loops, YMQ achieves a highly accurate mixed-precision layout instantly by analyzing layer importance metrics in log-space. The result is a custom mixed-precision portfolio that matches the low perplexity and high context stability of premium optimized quants (like AutoRound), while maintaining an ultra-lightweight, high-speed single-GPU cache footprint. --- ## πŸ› οΈ The YMQ Compilation Architecture Standard quantization pipelines treat network tensors like a flat dataset, applying destructive blanket low-bit compression to delicate tracking networks. The **YMQ-Compiler** solves high-context logic decay by parsing model files dynamically via an automated, multi-tiered protection matrix: 1. **Log-Space Gap Detection Clustering**: Instead of flat percentage thresholds, the engine computes statistical cluster variances in log-space, successfully isolating intermediate logical reasoning spikes and elevating them to stable non-linear 4-bit (`IQ4_XS`) formats, while compressing idle fact-storage layers to aggressive 2-bit baselines. 2. **Fading Boundary Tapering**: Recognizes the extreme fragility of initial token entry data vectors, forcing an input wave cushion (`L00=IQ4_NL` β†’ `L01=IQ4_XS` β†’ `L02=IQ3_XXS`) that gradually stabilizes parameters before hitting the fallback pools. 3. **Dedicated Gate Insulation**: Hard-shields volatile parallel Transformer Multi-Head Attention and Mamba Linear State Space Model (SSM) routing paths, keeping context tracking perfectly noise-free. 4. **Asymmetric Vocabulary Shielding**: Fixes tied-weight boundary errors by mapping the final logit classification exit heads to robust configurations to completely eliminate formatting loops and API tag leakage under deep contexts. 5. **Native Next-N Speculative Stripping**: Processed with advanced pre-tokenizer stripping to ensure zero index offset drift or layer-shifting risks across hybrid configurations. --- ## πŸš€ Recommended Runtime Parameters (llama.cpp / llama-server) ``` $./llama-server -m models/Qwen3.8-27B-YMQ-M.gguf -ctk q8_0 -ctv q4_0 --ctx-size 245760 --mmproj proj/Qwen3.8-27B-Q8.mmproj \ --spec-type draft-mtp --spec-draft-n-max 2 --timeout 36000 --checkpoint-min-step 2048 --ctx-checkpoints 4 \ --n-predict -1 --temp 0.6 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 --jinja -fa ``` --- ## β˜• Support & Future R&D If the **YMQ-Compiler** builds saved your context window from collapsing or optimized your active development cycle speeds, consider buying a coffee to fund further low-level optimization research. Your support keeps the server nodes baking future model scales! πŸ‘‰ **[Support ZeroDigest Research on ko-fi](https://ko-fi.com/zerodigest)** --- ## πŸ“¦ Source Framework & Automation Code The compiler pipeline automation engine, setup thresholds, and structural mapping rules are open-source. To view the implementation details or compile your own custom models natively using this profile layout, visit the official development hub: πŸ‘‰ **[GitHub: ZeroDigest / YMQ-Compiler](https://github.com/minyor/ymq-compiler)**