kaitchup/Hy4-flash-dondon-GGUF

AI model by kaitchup

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Subscribe to my newsletter · Support dondon is a set of low-bit GGUF releases of Tencent’s Hy4-flash, from 37.8 GB to 64.9 GB of weights. Each file builds on a public GGUF (AtomicChat or Xylolabs) or on my own IQ1S, IQ1M, and IQ2XXS quantizations, using GSQ-Lite, a cheaper variant of GSQ from IST-DASLab: it learns one scale per output row of each matrix by distillation from BF16, and folds it into the existing GGUF block scales, so the files keep standard GGML types. Using the original GSQ should significantly improve the models. RCO-Q2KXS has the size of Q2KXS. For each tensor group, RCO picked which of the other dondon files to take it from. Held-out evaluation: 64 sequences of 512 tokens over 12 domains (math and multiple-choice reasoning, code reasoning, instruction following, multilingual web text, source code, math text, books, human chat, mixed reasoning traces, agentic coding, and English web…

kaitchup/Hy4-flash-dondon-GGUF on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-21T08:20:39.846Z

Inside the original model card — Document outline
  1. Hy4-flash-dondon-GGUF
  2. Models
  3. Precision by layer
  4. GPQA Diamond
  5. Run with llama.cpp
  6. Papers and credits

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

kaitchup/Hy4-flash-dondon-GGUF is a task-unspecified model repository published by kaitchup on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-11-21T06:14:42.000Z
Last modified
2026-11-21T06:49:26.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-21T07:02:33.996Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models