Qwen3.8 27B GSQ RCO needs about 11.3 GB of memory at IQ2_S (a 9.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 0.0 GB to 12.1 GB (IQ3_S).
Qwen3.8-27B GSQ RCO – a vision‑enabled 27B GGUF model with non‑uniform quantization
Qwen3.8-27B GSQ RCO is a 27 billion‑parameter vision‑language model released under Apache‑2.0. It uses GSQ and RCO to assign per‑tensor quantization types, producing several GGUF files ranging from 8 GB to 12 GB. The model supports image and video understanding and runs unmodified in llama.cpp, Ollama, and LM Studio.
Good at
- Vision‑language tasks
- Long‑horizon reasoning
- Agentic planning
Limits
- No text‑only inference without vision projector
- Requires at least 8 GB VRAM for the smallest quant
- No built‑in tools beyond vision
Best for
- Multimodal document analysis
- Video summarization
- Complex multi‑step task execution
Who it’s for. Developers needing a dense, vision‑enabled LLM for local deployment. The model is suitable for applications that require reliable reasoning and multimodal input without external APIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ2_XS | 8.4 GB | 9.9 GB | Too big | Get file → | |
| IQ2_XS | 8.8 GB | 10.3 GB | Too big | Get file → | |
| IQ2_S | 9.3 GB | 10.9 GB | Too big | Get file → | |
| IQ2_S | 9.6 GB | 11.3 GB | Too big | Get file → | |
| IQ3_XXS | 10.1 GB | 11.8 GB | Too big | Get file → | |
| IQ3_XXS | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_S | 11.8 GB | 13.7 GB | Too big | Get file → | |
| IQ3_S | 12.1 GB | 14.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (≈9.9 GB memory at 8k context). With 10 GB VRAM, IQ3_XXS (≈12.2 GB memory) offers better quality. For 12 GB VRAM, IQ3_S (≈14.1 GB memory) provides the highest fidelity.
What GPU do you need for Qwen3.8 27B GSQ RCO?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XXS (10.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_S (12.1 GB file, about 14.1 GB in use).
Which Qwen3.8 27B GSQ RCO quant should you choose?
IQ2_S (9.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.8 27B GSQ RCO
How much VRAM does Qwen3.8 27B GSQ RCO need?
About 11.3 GB at IQ2_S with an 8K context window. That is the 9.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen3.8 27B GSQ RCO on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.8 27B GSQ RCO GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XS is 8.4 GB, IQ2_XS is 8.8 GB, IQ2_S is 9.3 GB, IQ2_S is 9.6 GB, IQ3_XXS is 10.1 GB and 3 more.
Where can I download Qwen3.8 27B GSQ RCO GGUF?
The files are on Hugging Face in the ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3.8 27B GSQ RCO use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Qwen3.8-27B GSQ RCO on 8 GB VRAM?
The smallest quant (IQ2_XS) requires about 9.9 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does the model support text‑only inference?
The GGUF files include a vision projector; text‑only inference is possible but the model is optimized for multimodal use.
What license applies to this model?
The model is released under the Apache‑2.0 license.