CoolFace
Modelpublic

zerodigest/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-YMQ-GGUF

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face
15likes13kdownloads
Model Card

<!-- zerodigest-lab-banner-v2-mid-tone --> <div style="background: #1f1f23; color: #f4f4f5; padding: 20px; border: 1px solid #38bdf8; border-radius: 8px; margin: 20px 0; font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;"> <h2 style="color: #38bdf8; margin: 0 0 10px 0; font-size: 18px; font-weight: 700; letter-spacing: -0.5px;">⚡ Fuel the Lab: Keep the Optimization Loops Running</h2> <p style="font-size: 14px; line-height: 1.5; margin: 0 0 16px 0; color: #d4d4d8;">Every single <b>ZeroDigest YMQ-MTP</b> release is handcrafted and manually calibrated via intensive importance-matrix sweeps to protect critical logic pathways. This project is entirely independent research—no automation bots, no corporate backers, and no external funding. Running multi-hour compute arrays consumes massive local infrastructure overhead out-of-pocket. Consider checking out our compiler or supporting our compute costs!</p> <div style="background: #18181b; padding: 12px; border-radius: 6px; border: 1px solid #3f3f46; font-size: 13px;"> <p style="margin: 0 0 8px 0; font-weight: 600; color: #f4f4f5;">👉 Developer Resources & Support Paths:</p> <div style="margin-bottom: 6px;">🛠️ <a href="https://github.com/minyor/ymq-compiler" target="blank" style="color: #38bdf8; text-decoration: underline; font-weight: bold;">View Compiler Source on GitHub (YMQ v2.0)</a></div> <div style="margin-bottom: 6px;">🚀 <a href="https://runpod.io?ref=dbjmkmeh" target="blank" style="color: #38bdf8; text-decoration: underline; font-weight: bold;">Deploy weights on RunPod Cloud Compute (Affiliate Link)</a></div> <div style="margin-bottom: 8px;">☕ <a href="https://ko-fi.com/zerodigest" target="_blank" style="color: #38bdf8; text-decoration: underline; font-weight: bold;">Support the Lab on Ko-fi (One-Time / Monthly)</a></div> <div style="margin: 8px 0; border-top: 1px solid #3f3f46;"></div> <div style="margin-bottom: 4px; font-family: monospace;">🧡 <span style="color: #f97316; font-weight: bold;">BTC:</span> <code style="background: #27272a; padding: 1px 4px; border-radius: 4px; color: #f4f4f5;">14Fmic9z3VA1ZU11bWoP6JtU7csTAApwZo</code></div> <div style="font-family: monospace;">🔷 <span style="color: #6366f1; font-weight: bold;">ETH/USDT:</span> <code style="background: #27272a; padding: 1px 4px; border-radius: 4px; color: #f4f4f5;">0xbe4cdc3adc27c21ef1c27c6b403311db07b35ed2</code></div> </div> </div>

Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-YMQ-GGUF

Source Model: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

⚖️ An Architecture-Aware, AutoRound-Inspired Mixed Precision Layout

This repository features advanced, custom architecture-aware quantizations of Qwen3.8-27B Cold-Fusion GAIN V1.1 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).

<p align="center"> <img src="./logo.jpg" width="800" alt="ZeroDigest YMQ Logo"> </p>

📊 Quantization Preset Tier Details

Preset TierTotal SizeTarget Usage / VRAM ProfileCognitive Real-World Coding Quality
XXS-Pro~9.1 GB⚠️ Experimental Low-VRAM SandboxThe Ultra-Compact Frontier.
XS-TI~9.8 GB⚡ 12GB Card Lifeline (High-Context)The 12GB Context Champion. Safely pins core attention layers to a stable IQ3_XXS gradient while crushing non-critical auxiliary arrays to IQ2_XS.
XS-Pro~10.6 GB⚡ Dedicated 12GB VRAM ChampionThe 12GB Efficiency Miracle. Features a highly optimized IQ4_XS/IQ3_XS gradient that keeps the model running fully inside VRAM with a clean 1.6GB context headroom buffer.
S-Pro~12.5 GB💎 Premium 16GB Workstation DriverThe Efficiency Miracle. Holds an elite 6.50 PPL for pristine conversational fluidness while using full Q5_K attention armor.
M-TI~12.6 GB💎 Premium 16GB GPU Workspace DriverThe 16GB Workstation Choice. Employs a robust Q5_K/IQ4_XS mixed-precision gradient that protects logical reasoning focus while leaving over 3.4GB of VRAM wide open.
M~14.5 GB🎯 High-Context Agent Workspace (Recommended)The Flagship Masterpiece. Heavy structural shielding for maximum logical durability across massive enterprise repositories.
L-TI~14.1 GB🔥 Heavy 16GB Workstation Choice (Precision)The 16GB High-Fidelity Champion. Features a robust Q6_K/IQ4_NL armored peak [local]. Minimizes information entropy drift to keep structural logic stable over long, multi-turn agent execution loops.

🎯 Quick Selection Guide

Use CaseRecommended PresetWhy
12GB GPUXS-TI or XS-ProBest 12GB card performance with high-context support
16GB GPU (Recommended)M-TI or S-ProThe sweet spot for coding tasks with optimal VRAM headroom
24GB GPUL-TI or M~14GB models fit well on 24GB VRAM with headroom for context
Low-VRAM / ExperimentalXXS-ProSub-10GB footprint for testing and lightweight workflows

📉 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 VariantFile SizePerplexityMean KL-DivergenceInternal Bit Gradient (High ➔ Mid ➔ Low ➔ Default ➔ Floor)
`XXS-Pro`~9.1 GB7.23360.185361 ± 0.0021IQ3_XXS ➔ IQ3_XXS ➔ IQ2_S ➔ IQ2_S ➔ IQ2_XXS
`XS-TI`~9.8 GB7.00680.168378 ± 0.001935IQ3_XXS ➔ IQ3_XXS ➔ IQ3_XXS ➔ IQ3_XXS ➔ IQ2_XXS
`XS-Pro`~10.6 GB6.79870.135866 ± 0.0018IQ4_XS ➔ IQ3_XXS ➔ IQ3_XXS ➔ IQ3_XXS ➔ IQ2_XXS
`S-Pro`~12.5 GB6.5087`0.080403 ± 0.0014`Q5_K ➔ IQ3_S ➔ IQ3_XXS ➔ IQ3_XXS (No Floor)
`M-TI`~12.9 GB6.62900.104087 ± 0.0016Q5_K ➔ IQ4_XS ➔ IQ3_S ➔ IQ3_XXS ➔ IQ2_XXS
`M`~14.5 GB6.36630.053286 ± 0.0013Q5_K ➔ IQ4_XS ➔ IQ3_S ➔ IQ3_XXS (No Floor)
`L-TI`~14.1 GB6.5786`0.086571 ± 0.0013`Q6_K ➔ IQ4_NL ➔ IQ4_XS ➔ IQ3_S ➔ IQ2_XS

💡 The Multi-Tier Grid Breakthrough: Standard S vs. S-Pro

During intensive local workspace validation passes, our architecture-aware YMQ-Compiler successfully mapped out a radical new bit-allocation matrix. By splitting the layer distribution, we created a premium, high-fidelity alternative to our standard budget tier:

  • —`S-Pro` Preset (~12.5 GB): Perplexity = 6.5087. By aggressively compressing auxiliary tensor lanes down to Q2_K but raising the background baseline floor to IQ3_XXS, S-Pro eliminates a massive wave of background quantization noise while only adding a few megabytes of file weight.

The practical result is a premium, low-overhead everyday driver for 16GB GPU setups. Backed by full `Q5_K` reasoning armor.

⚖️ 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.

🛠️ 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. 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. 2.Fading Boundary Tapering: Recognizes the extreme fragility of initial token entry data vectors, forcing an input wave cushion (L00=IQ4_NL → L01=IQ4_XS → L02=IQ3_XXS) that gradually stabilizes parameters before hitting the fallback pools.
  3. 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. 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. 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.

🚀 Recommended Runtime Parameters (llama.cpp / llama-server)

Need to scale up? Deploy this exact script on on-demand cloud GPUs via [RunPod Cloud Compute](https://runpod.io?ref=dbjmkmeh).

$./llama-server -m models/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-YMQ-M.gguf -ctk q8_0 -ctv q4_0 --ctx-size 245760 --mmproj models/mmproj-Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-Q6_K.gguf \
  --spec-type draft-mtp --spec-draft-n-max 3 --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

🖼️ Vision Projection (--mmproj)

For multimodal vision support, pair these builds with one of the following projection files:

VariantFileSizeNotes
Full Precision (F16)mmproj-F16.gguf~928 MBFull-precision vision tower. Maximum fidelity for image reasoning tasks.
Q6_Kmmproj-Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-Q6_K.gguf (this repo)~587 MBHigh-fidelity quantized vision tower. Excellent quality-to-size balance with minimal perceptible degradation.
Q4_K_Smmproj-Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-Q4_K_S.gguf (this repo)~478 MBCompact vision projection for VRAM-constrained setups. Retains strong image understanding at reduced footprint.

Pass via --mmproj <path-to-file> in your llama-server invocation (see example above).

☕ 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!

👉 [Support ZeroDigest Research on ko-fi](https://ko-fi.com/zerodigest)

📦 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:

👉 [GitHub: ZeroDigest / YMQ-Compiler](https://github.com/minyor/ymq-compiler)