ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF — new model trending #30 on Hugging Face

Exact file identities are recorded in [release-manifest.json](release-manifest.json) and [SHA256SUMS](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/SHA256SUMS).

## Evaluation

KLD measures the divergence of the quantized model's next-token distribution from **Swift 1.5 BF16**; lower is better. Development measurements use `wiki.test.raw`, 100 chunks and a **512-token context**. Development data informed refinement and is not independent validation.

The held-out results below use C4 prose, CodeParrot code, GSM8K math text and multilingual mC4 text. Prose/code/math use 100 chunks each; German/French/Spanish/Chinese use 25 chunks each, all at context 512. These are distributional KLD measurements, not task accuracy or math benchmark scores.

| Held-out text | IQ2_XS | IQ2_S | IQ3_XXS | IQ3_S |

| --- | ---: | ---: | ---: | ---: |

| C4 prose | 0.161594 | 0.107438 | 0.080238 | 0.041748 |

| CodeParrot code | 0.120884 | 0.084739 | 0.062546 | 0.035447 |

| GSM8K math text | 0.117467 | 0.096348 | 0.075964 | 0.043916 |

| German | 0.124482 | 0.091422 | 0.074645 | 0.035698 |

| French | 0.166785 | 0.113277 | 0.077791 | 0.046219 |

| Spanish | 0.082313 | 0.056393 | 0.039906 | 0.024186 |

| Chinese | 0.207063 | 0.129485 | 0.103141 | 0.052241 |

All four refined files improve KLD over their matched Swift starting quantizations on all seven reporting domains. Results are not uniformly better than the ISTA comparison quants: math-text KLD is 4.9–7.7% higher, and IQ3_S is higher on five of seven domains. ISTA comparisons measure each quant against its **own corresponding BF16 model**; they are not direct Swift-versus-Qwen task rankings or proof of equivalent capability.

The [full result table](evaluation/heldout-kld.tsv) includes the matched Swift starting quant, ISTA comparison and reported error estimates. [Evaluation metadata](evaluation/report.json) binds results to the exact released identities. A lexical overlap screen was applied against calibration/development text; it does not establish semantic deduplication or prove absence of overfitting. These 512-token tests do not establish quality at 32K or longer contexts.

## Usage

Use a llama.cpp build that supports Qwen3.8. Authenticate with an account granted access while this repository is private.

```bash

hf download ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf --local-dir .

llama-server \

-m Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf \

--jinja -fa on -ngl 99 -c 262144 \

--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 \

--presence-penalty 0.0 --repeat-penalty 1.0 --port 8000

```

Set the context size to fit available memory. The example context setting is not a claim that these quants were evaluated at that length.

This release provides the language-model GGUFs. A Swift 27B vision projector has not been verified for this release, so no projector or validated vision example is included.

## Quantization procedure

1. Reuse the published ISTA GSQ-RCO per-tensor allocation for each matching Qwen3.8-27B tier.

2. Quantize Swift 1.5 weights with the Swift V1MIX importance matrix and the selected allocation.

3. Apply Swift-specific GSQ refinement. IQ2_XS and IQ3_XXS use the preserved fixed-objective variants; IQ2_S and IQ3_S use their preserved V1MIX variants.

4. Freeze exact file identities, run the reporting evaluations, and preserve the matching MTP packages.

This release reuses ISTA's allocation search results; it does not claim a new RCO search on Swift. The [archived recipe records](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/RECIPE.txt) document construction settings and historical candidates; the release manifest identifies the selected files. The Swift importance matrix is included as [imatrix-swift15-v1mix.gguf](imatrix-swift15-v1mix.gguf).

Per-tensor assignments for all eight files are included in [tensor-allocation](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/tree/main/tensor-allocation). Each dump records the model SHA256, tensor count and type histogram. MTP dumps contain the 851 model tensors plus 15 head tensors.

## Methods and acknowledgements

GSQ and RCO were developed by the Deep Algorithms and Systems Lab at the Institute of Science and Technology Austria. This Swift adaptation is by UkisAI.

- **GSQ:** [paper](https://arxiv.org/abs/2604.18556) · [code](https://github.com/IST-DASLab/GSQ)

- **RCO:** [paper](https://arxiv.org/abs/2605.00649) · [code](https://github.com/IST-DASLab/RCO)

- **GGUF runtime and conversion:** [llama.cpp](https://github.com/ggml-org/llama.cpp)

We acknowledge the Qwen team for the original model, ISTA-DASLab for the quantization methods and published allocations, and NVIDIA Innovation Lab, AWS and Google Cloud for supporting Swift development.

## License and access

These adapted weights are distributed under the [Swift Open License v1.0](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/LICENSE). The original Qwen components retain their [Apache 2.0 license](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/LICENSE-APACHE-2.0) and [NOTICE](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/NOTICE). See the Swift license for applicable terms and enterprise licensing information.

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF