Underdog Saluki 27B 1.0 needs about 10.5 GB of memory at its main file (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Underdog Saluki 27B 1.0 – a 27 B Qwen model in a 7.9 GB GGUF file
Underdog Saluki 27B 1.0 is a 27 B Qwen model quantized with GSQ‑RCO for non‑uniform precision. The GGUF file is 7.9 GB and requires about 10.5 GB of VRAM at 8 k context. It supports tool calling and can be extended with a vision projector add‑on.
Good at
- Tool calling
- Multimodal vision with add‑on
- Large context (262 144 tokens)
Limits
- Requires ~10.5 GB VRAM at 8 k context
- Main file is text‑only; vision needs separate 0.6‑0.9 GB add‑on
- Apache 2.0 license
Best for
- Chatbots needing tool calls
- Agents that process long documents
- Multimodal applications with vision add‑on
Who it’s for. Developers building chat or agent applications that require tool calling and large context. The model is suitable for users with GPUs that can accommodate ~10 GB VRAM and who need a standard GGUF for llama.cpp, Ollama or LM Studio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.9 GB | 10.5 GB | Too big | Get file → |
The only available quant is the unknown quant with a 7.9 GB file. For 8 GB VRAM, this model is too large. If you have 10 GB or more VRAM, the model can run at 8 k context. No other quants are provided.
What GPU do you need for Underdog Saluki 27B 1.0?
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: the best quant that fits is the main file (7.9 GB file, about 10.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Underdog Saluki 27B 1.0
How much VRAM does Underdog Saluki 27B 1.0 need?
About 10.5 GB at its main file with an 8K context window. That is the 7.9 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 Underdog Saluki 27B 1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Underdog Saluki 27B 1.0 GGUF?
It depends on the quant: file is 7.9 GB.
What context length does Underdog Saluki 27B 1.0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Underdog Saluki 27B 1.0 GGUF?
The files are on Hugging Face in the ConwayResearch/Underdog-Saluki-27B-1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Underdog Saluki 27B 1.0 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 Underdog Saluki 27B 1.0 on 8 GB VRAM?
No. The model requires about 10.5 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision out of the box?
The main GGUF is text‑only. Add the vision projector file (0.6‑0.9 GB) to enable image processing.
What license does the model use?
Apache 2.0. The model and its quantizations are released under the Apache 2.0 license.