Qwen3.8 27B Ridge needs about 15.3 GB of memory at its main file (a 12.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Dense 27B Qwen model with native vision and reasoning
Qwen3.8-27B Ridge is a 27‑billion‑parameter dense model built on the Qwen3.5 architecture. It supports text, image, and video input and offers strong reasoning and long‑horizon agentic capabilities. The GGUF file is 12.6 GB and requires about 15.3 GB of VRAM at an 8 k context.
Good at
- Reasoning and multi‑step tasks
- Native vision‑language understanding
- Long‑horizon agentic planning
Limits
- Requires ~15 GB VRAM at 8 k context
- Vision model separate (0.87 GB)
- Apache‑2.0 license
Best for
- Complex coding assistance
- Agentic task execution
- Vision‑based document analysis
Who it’s for. Developers and researchers who need a single dense model that handles text, images, and videos without external vision modules. The model is suitable for on‑premise deployment where license compliance and performance are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.6 GB | 15.3 GB | Too big | Get file → |
The provided GGUF file is unquantized and 12.6 GB. For 16–24 GB VRAM, this file fits comfortably. If a smaller model is needed, no other quantizations are listed, so use the unquantized file and adjust context size to stay within memory limits.
What GPU do you need for Qwen3.8 27B Ridge?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is the main file (12.6 GB file, about 15.3 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.8 27B Ridge
How much VRAM does Qwen3.8 27B Ridge need?
About 15.3 GB at its main file with an 8K context window. That is the 12.6 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 Ridge on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.8 27B Ridge GGUF?
It depends on the quant: file is 12.6 GB.
What context length does Qwen3.8 27B Ridge support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Qwen3.8 27B Ridge GGUF?
The files are on Hugging Face in the empero-ai/Qwen3.8-27B-Ridge-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 Ridge 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 Ridge on a GPU with 8 GB VRAM?
No. The model needs about 15.3 GB of VRAM at an 8 k context, so 8 GB is insufficient.
Is the vision component included in the GGUF file?
The GGUF file contains only the language weights. Add the separate 0.87 GB mmproj file for image and video input.
Does the model support only text or also images?
It supports both text and vision; the vision encoder is a separate BF16 mmproj that must be loaded alongside the GGUF.