ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
image-text-to-text model by ISTA-DASLab
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A 512-expert mixture-of-experts model with half of its experts removed, targeted at code and retaining multimodal capability. 58.4 GB against 354 GB at BF16, an effective 1.89 bits per parameter of the original transformer. [](https://arxiv.org/abs/2604.18556) [](https://arxiv.org/abs/2605.00649) [](https://github.com/IST-DASLab/GSQ) [](https://github.com/IST-DASLab/RCO) [](https://github.com/IST-DASLab) [](#license) This release is a capability-targeted compression of Qwen3.8-Flash-Next. Half of the routed experts are removed from the model rather than quantized, and the remaining weights are stored at 3.5 bpw. The base model has 176.9B parameters and occupies 354 GB at BF16. The compressed model reduces to only 29.6 GB which must reside in memory: the n-gram shard is a lookup table and may be served from disk. The resident working set of a 176.9B-parameter model is therefore within the capacity of a single 32 GB accelerator. Averaged over the transformer, this corresponds to 1.89 bits per parameter of the original model. The figure is an effective rate: it amortises…
Read the full model card ↗ · Preview checked 2026-11-14T12:00:07.020Z
Inside the original model card — Document outline
- Qwen3.8-Flash-Next · GSQ-RCO Coder
- Overview
- What Expert Pruning Is
- How the Experts Are Chosen
- Vision Capability
- Available Files
- llama.cpp
- Strata Engine
- Method
- Citation
- Acknowledgements
- License
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. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF is a image-text-to-text model repository published by ISTA-DASLab on Hugging Face. The source reports the gguf library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- gguf
- Recent downloads (30 days)
- 779,220
- Cumulative likes
- 615
- Hugging Face trending score
- 29
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-26T09:42:51.000Z
- Last modified
- 2026-10-19T17:48:41.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-Flash-Next
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-14T06:59:45.906Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.